CN109241334A - Audio keyword quality detecting method, device, computer equipment and storage medium - Google Patents
Audio keyword quality detecting method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109241334A CN109241334A CN201810927508.4A CN201810927508A CN109241334A CN 109241334 A CN109241334 A CN 109241334A CN 201810927508 A CN201810927508 A CN 201810927508A CN 109241334 A CN109241334 A CN 109241334A
- Authority
- CN
- China
- Prior art keywords
- recording file
- audio
- file
- time point
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Signal Processing For Digital Recording And Reproducing (AREA)
Abstract
本发明公开了一种音频关键字质检方法，用于解决录音文件质检效率低下的问题。本发明提供的方法包括：确定当前待质检的目标关键字；根据预先建立的音频时间对应关系确定出各个待质检的录音文件中存在所述目标关键字的目标录音文件，以及确定目标关键字所处的音频时间点，音频时间对应关系记录了需质检的关键字、识别文本中存在的需质检的关键字的待质检的录音文件以及存在的关键字位于录音文件音频中播放的时间点之间的对应关系，音频时间点是指目标关键字位于目标录音文件中播放的时间点；输出确定出的各个目标录音文件的文件信息，并标识各个所述目标录音文件中确定出的所述音频时间点。本发明还提供音频关键字质检装置、计算机设备及存储介质。
The invention discloses a method for quality inspection of audio keywords, which is used for solving the problem of low efficiency in quality inspection of recording files. The method provided by the present invention includes: determining a target keyword currently to be quality-checked; determining, according to a pre-established audio time correspondence, a target recording file containing the target keyword in each recording file to be quality-checked, and determining the target key The audio time point at which the word is located, and the audio time correspondence records the keywords that need quality inspection, the audio files that identify the keywords that need quality inspection existing in the text to be inspected, and the existing keywords are played in the audio of the recording file. The corresponding relationship between the time points, the audio time point refers to the time point when the target keyword is located in the target recording file and is played; output the file information of each target recording file determined, and identify each target recording file. of the audio time point. The present invention also provides an audio keyword quality inspection device, a computer device and a storage medium.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of methods of audio keyword quality inspection.
Background technique
Many enterprises are equipped with contact staff, and contact staff answers the consulting of client by being linked up with client and asks
Inscribe or facilitate the generation of transaction, enterprise can record to these service calls, arrange special quality inspection personnel inspection record in be
No there are violation language, so as to ensure the service quality of contact staff and avoid violation operation.
But for large enterprise, the recording quantity of service calls is very huge, meanwhile, quality inspection personnel inspection record
Sound will also take a substantial amount of time, and needing all to hear out a recording file can just know in the recording with the presence or absence of violation language
Speech, time-consuming and laborious and inefficiency.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of sound of working efficiency that can promote quality inspection personnel
Frequency keyword quality detecting method, device, computer equipment and storage medium.
A kind of audio keyword quality detecting method, comprising:
It determines currently to the target keywords of quality inspection；
Determine that there are the mesh in each recording file to quality inspection according to the audio time corresponding relationship pre-established
The target recording file of keyword is marked, and determines audio time point locating for the target keywords, wherein when the audio
Between corresponding relationship have recorded the corresponding relationship between keyword, keyed file and the keyword time point for needing quality inspection, it is described
Keyed file refers to the recording file to quality inspection that the keyword of quality inspection is needed present in identification text, the keyword time
Point refers to that the existing keyword is located at the time point played in recording file audio, and the audio time point refers to the mesh
Mark keyword is located at the time point played in target recording file；
The file information for each target recording file determined is exported, and identifies each target recording file
In the audio time point determined.
A kind of audio keyword quality inspection device, comprising:
Keyword determining module, for determining currently to the target keywords of quality inspection；
Recording file determining module, it is each to quality inspection for being determined according to the audio time corresponding relationship that pre-establishes
There are the target recording files of the target keywords in recording file, and when audio locating for the determining target keywords
Between point, wherein the audio time corresponding relationship has recorded keyword, keyed file and the keyword time point for needing quality inspection
Between corresponding relationship, the keyed file refer to identification text present in need quality inspection keyword the recording to quality inspection
File, the keyword time point refers to that the existing keyword is located at the time point played in recording file audio, described
Audio time point refers to that the target keywords are located at the time point played in target recording file；
The file information output module for exporting the file information for each target recording file determined, and is marked
Know the audio time point determined in each target recording file.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize above-mentioned audio keyword quality detecting method when executing the computer program
The step of.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
The step of calculation machine program realizes above-mentioned audio keyword quality detecting method when being executed by processor.
Above provide a kind of audio keyword quality detecting method, device, computer equipment and storage mediums, firstly, determining
Currently to the target keywords of quality inspection；Then, it is determined according to the audio time corresponding relationship pre-established each to quality inspection
There are the target recording files of the target keywords in recording file, and when audio locating for the determining target keywords
Between point, wherein the audio time corresponding relationship has recorded keyword, keyed file and the keyword time point for needing quality inspection
Between corresponding relationship, the keyed file refer to identification text present in need quality inspection keyword the recording to quality inspection
File, the keyword time point refers to that the existing keyword is located at the time point played in recording file audio, described
Audio time point refers to that the target keywords are located at the time point played in target recording file；Finally, what output was determined
The file information of each target recording file, and when identifying the audio determined in each target recording file
Between point.In this way, when quality inspection personnel needs to check the violation language for whether occurring the keyword that some needs quality inspection in these recording files
Yan Shi directly can navigate to the recording file there are keyword by the audio time corresponding relationship, and identify the recording
There are the audio time of keyword points in file, and quick positioning of the keyword in recording file may be implemented, facilitate quality inspection
Personnel quickly verify in the recording file whether really there is violation language, substantially increase the effect of the work to recording file quality inspection
Rate.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application environment schematic diagram of one embodiment of the invention sound intermediate frequency keyword quality detecting method；
Fig. 2 is a flow chart of one embodiment of the invention sound intermediate frequency keyword quality detecting method；
When Fig. 3 is that one embodiment of the invention sound intermediate frequency keyword quality detecting method pre-establishes audio under an application scenarios
Between corresponding relationship flow diagram；
Fig. 4 is that one embodiment of the invention sound intermediate frequency keyword quality detecting method plays target recording text under an application scenarios
Part and the flow diagram positioned；
Fig. 5 is that process of the one implementation sound intermediate frequency keyword quality detecting method step 302 of the present invention under an application environment is shown
It is intended to；
Fig. 6 is the structural schematic diagram of one embodiment of the invention sound intermediate frequency keyword quality inspection device；
Fig. 7 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
A kind of audio keyword quality detecting method provided by the present application, can be applicable in the application environment such as Fig. 1, wherein eventually
End is communicated by network with server.Wherein, the terminal can be, but not limited to various personal computers, laptop,
Smart phone, tablet computer and portable wearable device.Server can use independent server either multiple servers
The server cluster of composition is realized.
In one embodiment, it as shown in Fig. 2, providing a kind of audio keyword quality detecting method, applies in Fig. 1 in this way
Server for be illustrated, include the following steps:
101, it determines currently to the target keywords of quality inspection；
In the present solution, quality inspection personnel can first determine the current keyword for preparing quality inspection, the i.e. target keywords.Specifically
Ground, the system of server can on interface by the keyword of quality inspection in need show quality inspection personnel to select, quality inspection personnel
Selection one, two or more keywords are as currently to the target keywords of quality inspection in the keyword shown from these.
It is understood that needing the keyword of quality inspection can be preparatory according to the needs of actual conditions by administrator in system
Setting, can manage these keywords by a character library, and administrator can be in the key in terminal addition, deletion character library
Word, to realize the management to the keyword for needing quality inspection.
102, determine that there are institutes in each recording file to quality inspection according to the audio time corresponding relationship pre-established
The target recording file of target keywords is stated, and determines audio time point locating for the target keywords, wherein the sound
Frequency corresponding time relationship has recorded the corresponding relationship between keyword, keyed file and the keyword time point for needing quality inspection,
The keyed file refers to the recording file to quality inspection that the keyword of quality inspection is needed present in identification text, the keyword
Time point refers to that the existing keyword is located at the time point played in recording file audio, and the audio time point refers to institute
It states target keywords and is located at the time point played in target recording file；
It is understood that in simple terms, audio time corresponding relationship is exactly to have recorded keyword, recording file and the pass
Key word is in relationship between play time in the recording file.For example the recording substance of some recording file A is " purchase XXX
Insurance can be returned 200 yuan existing ... ", wherein " returning existing " word is the keyword of quality inspection, which appears in recording file A
The 3rd point of 40 seconds time point position, therefore, audio time corresponding relationship can be by keyword " return existing ", recording file A and the
3 points of 40 seconds this time point associated storages, establish the corresponding relationship of three.
Further, such as Fig. 3, the audio time corresponding relationship can pre-establish as follows:
201, each recording file to quality inspection is obtained；
202, each recording file to quality inspection carries out speech recognition, obtains and each recording file pair to quality inspection
The identification text answered, while recording the time point that the identification text plays in corresponding recording file；
203, it needs the keyword of quality inspection to be compared with default respectively in each identification text, determines keyed file
And keyword time point；
204, it is built according to the corresponding relationship between the keyword for needing quality inspection, keyed file and keyword time point
Found the audio time corresponding relationship.
For step 201, firstly, it is necessary to obtain those recording files for waiting for quality inspection.On the server, it can all generate daily
A large amount of recording file may be set in the recording file that the daily period in morning obtains these without quality inspection in this programme
Carry out pre-establishing for audio time corresponding relationship.
It, can be using speech recognition technology to this after getting these and waiting for the recording file of quality inspection for step 202
A little recording files carry out speech recognition, obtain the corresponding identification text of each recording file to quality inspection.In the present solution, considering
The quantity of recording file is often more huge, therefore server can be allowed to execute voice again in the period in morning in a manner of running and criticize
The step of identification, to complete the processing work of speech recognition using the free time section of server system.In speech recognition
While, it is also necessary to the time that the identification text that server also needs record identification to obtain plays in corresponding recording file
Point.Such as the recording substance of some recording file A is " purchase XXX insurance, can return 200 yuan existing ... ", wherein " purchase " one
The play time of word be the 3rd point 36 seconds, the play time of " insurance " word be the 3rd point 38 seconds, the broadcasting of " can with " word
Time point be the 3rd point 39 seconds, the play time of " return existing " word be the 3rd point 40 seconds, the play time of " 200 yuan " word is
3rd point 41 seconds, etc..
For step 203, it is to be understood that above-mentioned steps 202 are identified to obtain each recording file to quality inspection
Corresponding identification text, and have recorded the play time of text in these identification texts.In this case, it need to only detect each
Which text belongs to keyword in a identification text, finds keyword and obtains the corresponding play time of keyword, can obtain
Know that these need the keyword of quality inspection to appear in which recording file, and appears in the play time in recording file, from
And the corresponding relationship of three is established, obtain the audio time corresponding relationship.
For step 204, it is known that, determine that there are the recording of the keyword for needing quality inspection in identification text in step 203
File and the existing keyword were located on the basis of the time point played in recording file audio, and step 204 is according to " need
The keyword of quality inspection ", " there are the recording files of the keyword for needing quality inspection in identification text " and " the existing key
Word is located at the time point played in recording file audio " corresponding relationship between three can establish that the audio time is corresponding to close
System.For example, accepting the example above, it is assumed that the keyword for needing quality inspection includes " purchase " and " insurance ", by the inspection to recording file A
It surveys, it is found that the identification text of recording file A has " purchase " and " insurance " the two keywords, therefore can establish to obtain
" purchase-recording file A- the 3rd point 36 seconds " and " insurance-recording file A- the 3rd point and 38 seconds " the two audio times are corresponding closes
System.It is found that can similarly establish other audio time corresponding relationships with 201-204 through the above steps.
103, the file information for each target recording file that output is determined, and identify each target recording
The audio time point determined in file.
When determining each target recording file, namely knows in which target recording file and be likely that there are
Belong to the keyword of " violation language ", this is that quality inspection personnel needs are known, quality inspection personnel can be helped from a large amount of recording text
Preliminary screening is carried out in part, therefore, it is also desirable to export the file information of these target recording files, such quality inspection personnel is in matter
These target recording files can be learnt when inspection.Wherein, the file information can specifically include filename, storage positions of files, record
One or more of information such as both persons' information, the long recording time talked in sound file.In addition, this programme is for the ease of matter
Inspection personnel quickly navigate in recording file each target record that there are the positions of quality inspection keyword, also determine in output
The audio time point determined in each target recording file is identified while the file information of sound file.By above-mentioned
Content is it is found that audio time point here is exactly that the target keywords are located at the time point played in target recording file.
Further, for the audio that quality inspection personnel of being more convenient for listens to these target recording files, this programme is also in determination
These target recording files are played automatically after target recording file, and play position is automatically positioned to audio time point
Anterior locations, so that quality inspection personnel is without wasting playback file from the beginning of a large amount of time, without manually will be current
Play position is positioned to the audio time point, further improves quality inspection personnel to the effect of these target recording file quality inspections
Rate.As Fig. 4 can also include: after determining each target
301, a target recording file is chosen from each target recording file as currently playing current record
Sound file；
302, determine that the current recording file starts to broadcast according to the current recording file corresponding audio time point
Put time point；
303, the current recording file is played since the broadcast start time point.
For step 301, since quality inspection personnel can only listen to a target recording file simultaneously, when target is recorded
When file is multiple, need therefrom to choose a target recording file as currently playing current recording file；If target
Recording file only one, then can by this target recording file choose as currently playing current recording file.
For step 302, which is the play time that target keywords are located in target audio file, this
In scheme, generally requires and listen to one time of content in target recording file to quality inspection personnel, therefore generally require and broadcasting
When putting current recording file, before the audio time point play namely broadcast start time point is located at audio time
Before point.
Further, such as Fig. 5, the current recording text is determined according to the corresponding audio time point of the current recording file
The broadcast start time point of part, the step 302 specifically can also include:
401, an earliest audio time point of time in the corresponding audio time point of the current recording file is determined
For first time point；
402, the time point for being located at a broadcasting before the first time point in the current recording file is determining
For the broadcast start time point of the current recording file.
For step 401 and step 402, it is contemplated that this there may be multiple audio time points in current recording file
In the case of, quality inspection personnel needs are listened the earliest audio time point of each audio time point since the current recording file
It takes, therefore, a wherein earliest audio time point can be determined as first time point, and will be before the first time point
The time point of one broadcasting is determined as the broadcast start time point of the current recording file.In this way, can guarantee quality inspection people
In the case that member has more than two audio time points in a current recording file, from an earliest audio time point
Front starts to play, and meets the requirement of quality inspection and listens to the habit of audio.
Further, this programme can specifically determine the broadcast start time point, the step by following two mode
Rapid 402 can specifically include:
Mode one: the time point for being located at a broadcasting before the first time point in the current recording file determines
For the broadcast start time point of the current recording file, the broadcast start time point can be specifically determined by two ways.
For example, 3 seconds before first time point time points can be determined as to the broadcast start time point of the first recording file.It illustrates
It is bright, it is assumed that the first recording file A includes two audio time points, and audio time point is the 2nd minute and 10 seconds, when another audio
Between point be 30 seconds the 2nd minute, then can cause first time point be the 2nd point 10 seconds, preset first when it is 3 seconds a length of, then can determine this
The broadcast start time point of first recording file A is the 2nd minute and 7 seconds.
Mode two: step 501 carries out audio analysis to the current recording file, obtains in the current recording file
Before the first time point, with the immediate speech pause point of the first time point；
Step 502, the speech pause point corresponding time point that will acquire are determined as the current recording file
Broadcast start time point.
For step 501 and 502, it is to be understood that in mode two, in order to fully consider that quality inspection personnel listens to audio
Efficiency, the content of current recording file is understood convenient for quality inspection personnel, can by find current recording file in voice stop
Pause point will be located at before first time point and with the immediate speech pause point of the first time point as current recording text
Part starts the position played.In this way, can not only allow the position for starting to play as close to first time point (i.e. current record
The audio time point of foremost in sound file), and the corresponding audio content in position that can to start to play be it is coherent,
It easily facilitates quality inspection personnel and understands content in current recording file.This is because the conversation content for the people that recording file is recorded,
For people in dialogue, speech is coherent but has with pausing, and starts to play if choosing a time point directly before first time point,
As soon as the position for being likely to start to play is located among a coherent speech or even among the pronunciation of some word, this is unfavorable for matter
Inspection personnel understand the content for this section of recording that will be heard.Therefore, this programme is by step 501 and 502, from speech pause point
Position starts to play, and will meet the rule of people's dialogue, also complies with the rule that quality inspection personnel listens to recording substance.It needs to illustrate
It is that can determine the position of speech pause point by analyzing the volume height of current recording file sound intermediate frequency.In a segment of audio
In, speech pause point is located at the volume lowest point of the section audio, because people dialogue when, pause point be exactly without pronounce or
Person's volume is very low, therefore can quickly determine the current recording file by the volume height of analysis current recording file sound intermediate frequency
In each speech pause point.Certainly, in order to which the operational capability and resource of saving server need to only divide when carrying out audio analysis
Analyse the audio section before first time point.Further, can specifically intercept in the current recording file close to this
One time point and the audio section for being located at the second duration before first time point.Such as a length of 10 seconds when second, then intercept this first
10 seconds audio sections carry out audio analysis before time point.This is because it is continuously to say without a break that common people, which talk with communication,
There is no pauses within words 10 seconds or more.Certainly, which can specifically be set according to the actual situation.
Further, after determining each target recording file, can also include:
Step 601, if it is determined that each target recording file quantity be greater than 1, then obtain each target
The recording time of recording file；
Step 602, the sequence that each target recording file is determined according to the sequencing of recording time；
Wherein, in the step 103 the step of " the file information for each target recording file that output is determined "
Specifically: the file information for each target recording file determined is exported to designated terminal, so that the specified end
End shows each target recording file according to the sequence.
For step 601 and step 602, it is contemplated that when exporting the file information of each target recording file, if output
Target recording file quantity it is excessive, these targets of quality inspection in an orderly manner recording text will be unfavorable for so that quality inspection personnel is felt at a loss
Part.Therefore, this programme can also determine the sequence of each target recording file according to the sequencing of recording time, defeated
Out when the file information of these target recording files, the file information for each target recording file determined will be exported
To designated terminal, so that the designated terminal shows each target recording file according to the sequence.
On the other hand, above-mentioned steps 303 play the current recording file since the broadcast start time point, can
Know, when current recording file finishes playing, and quality inspection personnel is after determining the quality inspection of current recording file on system interface,
Server can play next recording file automatically, at this point, the sequence played automatically can also be according to the successive of recording time
Sequence determines.
In conclusion currently being closed to the target of quality inspection above provide a kind of audio keyword quality detecting method firstly, determining
Then key word is determined to exist in each recording file to quality inspection described according to the audio time corresponding relationship pre-established
Audio time point locating for the target recording file of target keywords and the target keywords, the audio time is corresponding to close
System have recorded need quality inspection keyword, identification text present in need quality inspection keyword to quality inspection recording file and deposit
The keyword be located at the corresponding relationship between the time point played in recording file audio, the audio time point refers to
The target keywords are located at the time point played in target recording file；Finally, each target record that output is determined
The file information of sound file, and identify the audio time point determined in each target recording file.As quality inspection people
It, can be directly by being somebody's turn to do when member needs to check the violation language for whether occurring the keyword that some needs quality inspection in these recording files
Audio time corresponding relationship navigates to the recording file there are keyword, and identifies the sound in the recording file there are keyword
Quick positioning of the keyword in recording file may be implemented in frequency time point, facilitates quality inspection personnel and quickly verifies recording text
Whether really there is violation language in part, substantially increases the working efficiency to recording file quality inspection.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of audio keyword quality inspection device is provided, the audio keyword quality inspection device and above-mentioned reality
A sound intermediate frequency keyword quality detecting method is applied to correspond.As shown in fig. 6, the audio keyword quality inspection device includes that keyword determines
Module 701, recording file determining module 702 and the file information output module 703, detailed description are as follows for each functional module:
Keyword determining module 701, for determining currently to the target keywords of quality inspection；
Recording file determining module 702, it is each to matter for being determined according to the audio time corresponding relationship pre-established
There are when audio locating for the target recording file of the target keywords and the target keywords in the recording file of inspection
Between point, the audio time corresponding relationship, which has recorded, needs the keyword of quality inspection present in the keyword for needing quality inspection, identification text
Pair being located between the time point played in recording file audio to the recording file of quality inspection and the existing keyword
It should be related to, the audio time point refers to that the target keywords are located at the time point played in target recording file；
The file information output module 703, for exporting the file information for each target recording file determined, and
Identify the audio time point determined in each target recording file.
Further, the audio time corresponding relationship can be pre-established by following module:
File acquisition module, for obtaining each recording file to quality inspection；
Speech recognition module, for carrying out speech recognition to each recording file to quality inspection, obtain with it is each to
The corresponding identification text of the recording file of quality inspection, while recording what the identification text played in corresponding recording file
Time point；
Comparison module is determined for needing the keyword of quality inspection to be compared with default respectively in each identification text
Keyed file and keyword time point；
Relationship establishes module, for according to the keyword for needing quality inspection, keyed file and keyword time point it
Between corresponding relationship establish the audio time corresponding relationship.
Further, the audio keyword quality inspection device can also include:
Recording file chooses module, for choosing a target recording file conduct from each target recording file
Currently playing current recording file；
Play time determining module, for working as according to the corresponding audio time point determination of the current recording file
The broadcast start time point of preceding recording file；
Recording file playing module, for playing the current recording file since the broadcast start time point.
Further, the play time determining module may include:
Earliest time determination unit, for by the time in the corresponding audio time point of the current recording file it is earliest one
A audio time point is determined as first time point；
Broadcast start time determination unit, for will be located at before the first time point in the current recording file
The time point of one broadcasting is determined as the broadcast start time point of the current recording file.
Further, it is determined that out after each target recording file, further includes:
Quantity determination unit, however, it is determined that the quantity of each target recording file gone out is greater than 1, then obtains each described
The recording time of target recording file；
Sequencing unit determines the sequence of each target recording file according to the sequencing of recording time；
Wherein, the file information output module specifically can be used for: each target recording file determined
The file information is exported to designated terminal, so that the designated terminal shows each target recording file according to the sequence.
Specific restriction about audio keyword quality inspection device may refer to above for audio keyword quality detecting method
Restriction, details are not described herein.Modules in above-mentioned audio keyword quality inspection device can be fully or partially through software, hard
Part and combinations thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can also be stored in a software form in the memory in computer equipment, execute the above modules in order to which processor calls
Corresponding operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 7.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data being related in frequency keyword quality detecting method.The network interface of the computer equipment is used
It is communicated in passing through network connection with external terminal.To realize a kind of frequency keyword matter when the computer program is executed by processor
Detecting method.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize that above-described embodiment sound intermediate frequency is crucial when executing computer program
The step of word quality detecting method, such as step 101 shown in Fig. 2 is to step 103.Alternatively, reality when processor executes computer program
The function of each module/unit of existing above-described embodiment sound intermediate frequency keyword quality inspection device, such as module 701 shown in Fig. 6 is to module
703 function.To avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of above-described embodiment sound intermediate frequency keyword quality detecting method, such as step shown in Fig. 2 when being executed by processor
Rapid 101 to step 103.Alternatively, realizing that above-described embodiment sound intermediate frequency keyword quality inspection fills when computer program is executed by processor
The function for each module/unit set, such as module 701 shown in Fig. 6 is to the function of module 703.It is no longer superfluous here to avoid repeating
It states.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of audio keyword quality detecting method characterized by comprising
It determines currently to the target keywords of quality inspection；
Determine that there are target passes in each recording file to quality inspection according to the audio time corresponding relationship pre-established
The target recording file of key word, and determine audio time point locating for the target keywords, wherein the audio time pair
Relation record is answered to need the corresponding relationship between keyword, keyed file and the keyword time point of quality inspection, the key
Word file refers to that the recording file to quality inspection that the keyword of quality inspection is needed present in identification text, the keyword time point are
Refer to that the existing keyword is located at the time point played in recording file audio, the audio time point refers to that the target is closed
Key word is located at the time point played in target recording file；
The file information for each target recording file determined is exported, and is identified in each target recording file really
The audio time point made.
2. audio keyword quality detecting method according to claim 1, which is characterized in that the audio time corresponding relationship is logical
Following steps are crossed to pre-establish:
Obtain each recording file to quality inspection；
Speech recognition is carried out to each recording file to quality inspection, obtains knowledge corresponding with each recording file to quality inspection
Other text, while recording the time point that the identification text plays in corresponding recording file；
It needs the keyword of quality inspection to be compared with default respectively in each identification text, determines keyed file and key
Word time point；
The sound is established according to the corresponding relationship between the keyword for needing quality inspection, keyed file and keyword time point
Frequency corresponding time relationship.
3. audio keyword quality detecting method according to claim 1, which is characterized in that determining each target record
After sound file, further includes:
A target recording file is chosen from each target recording file as currently playing current recording file；
The broadcast start time point of the current recording file is determined according to the corresponding audio time point of the current recording file；
The current recording file is played since the broadcast start time point.
4. audio keyword quality detecting method according to claim 3, which is characterized in that described according to the current recording text
The corresponding audio time point of part determines that the broadcast start time point of the current recording file includes:
When an earliest audio time point of time in the corresponding audio time point of the current recording file is determined as first
Between point；
A time point played being located at before the first time point in the current recording file is determined as described work as
The broadcast start time point of preceding recording file.
5. audio keyword quality detecting method according to any one of claim 1 to 4, which is characterized in that determining respectively
After a target recording file, further includes:
If it is determined that each target recording file quantity be greater than 1, then obtain the record of each target recording file
Time processed；
The sequence of each target recording file is determined according to the sequencing of recording time；
The file information for exporting each target recording file determined specifically: each mesh that will be determined
The file information of mark recording file is exported to designated terminal, so that the designated terminal shows each mesh according to the sequence
Mark recording file.
6. a kind of audio keyword quality inspection device characterized by comprising
Keyword determining module, for determining currently to the target keywords of quality inspection；
Recording file determining module, for determining each recording to quality inspection according to the audio time corresponding relationship pre-established
There are the target recording files of the target keywords in file, and determine audio time locating for the target keywords
Point, wherein the audio time corresponding relationship have recorded need quality inspection keyword, keyed file and keyword time point it
Between corresponding relationship, the keyed file refer to identification text present in need quality inspection keyword to quality inspection recording text
Part, the keyword time point refer to that the existing keyword is located at the time point played in recording file audio, the sound
Frequency time point refers to that the target keywords are located at the time point played in target recording file；
The file information output module for exporting the file information for each target recording file determined, and identifies each
The audio time point determined in a target recording file.
7. audio keyword quality inspection device according to claim 6, which is characterized in that the audio time corresponding relationship is logical
Following module is crossed to pre-establish:
File acquisition module, for obtaining each recording file to quality inspection；
Speech recognition module is obtained with each for carrying out speech recognition to each recording file to quality inspection to quality inspection
The corresponding identification text of recording file, while recording identification time for playing in corresponding recording file of text
Point；
Comparison module determines crucial for needing the keyword of quality inspection to be compared with default respectively in each identification text
Word file and keyword time point；
Relationship establishes module, for according between the keyword for needing quality inspection, keyed file and keyword time point
Corresponding relationship establishes the audio time corresponding relationship.
8. audio keyword quality inspection device according to claim 6 or 7, which is characterized in that the audio keyword quality inspection
Device further include:
Recording file chooses module, for choosing a target recording file from each target recording file as current
The current recording file of broadcasting；
Play time determining module, for determining the current record according to the corresponding audio time point of the current recording file
The broadcast start time point of sound file；
Recording file playing module, for playing the current recording file since the broadcast start time point.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of any one of 5 audio keyword quality detecting method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization audio keyword quality detecting method as described in any one of claim 1 to 5 when the computer program is executed by processor
The step of.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810927508.4A CN109241334A (en) | 2018-08-15 | 2018-08-15 | Audio keyword quality detecting method, device, computer equipment and storage medium |
| PCT/CN2018/123067 WO2020034538A1 (en) | 2018-08-15 | 2018-12-24 | Audio keyword quality inspection method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810927508.4A CN109241334A (en) | 2018-08-15 | 2018-08-15 | Audio keyword quality detecting method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109241334A true CN109241334A (en) | 2019-01-18 |
Family
ID=65070732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810927508.4A Pending CN109241334A (en) | 2018-08-15 | 2018-08-15 | Audio keyword quality detecting method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109241334A (en) |
| WO (1) | WO2020034538A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750230A (en) * | 2019-09-30 | 2020-02-04 | 北京淇瑀信息科技有限公司 | A voice interface display method, device and electronic device |
| CN112101311A (en) * | 2020-11-16 | 2020-12-18 | 深圳壹账通智能科技有限公司 | Double-recording quality inspection method and device based on artificial intelligence, computer equipment and medium |
| CN112509609A (en) * | 2020-12-16 | 2021-03-16 | 北京乐学帮网络技术有限公司 | Audio processing method and device, electronic equipment and storage medium |
| CN116092528A (en) * | 2022-12-30 | 2023-05-09 | 沈阳即时智能科技有限公司 | Audio quality inspection method and system |
| CN116346987A (en) * | 2023-04-18 | 2023-06-27 | 平安国际融资租赁有限公司 | A real-time audio quality inspection method and device, storage medium, and computer equipment |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10811618B2 (en) | 2016-12-19 | 2020-10-20 | Universal Display Corporation | Organic electroluminescent materials and devices |
| US10910570B2 (en) | 2017-04-28 | 2021-02-02 | Universal Display Corporation | Organic electroluminescent materials and devices |
| US10934293B2 (en) | 2017-05-18 | 2021-03-02 | Universal Display Corporation | Organic electroluminescent materials and devices |
| CN111935552A (en) * | 2020-07-30 | 2020-11-13 | 安徽鸿程光电有限公司 | Information labeling method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011053563A (en) * | 2009-09-03 | 2011-03-17 | Neikusu:Kk | Collation system of voice keyword in voice data, method thereof, and collation program of voice keyword in voice data |
| CN105141787A (en) * | 2015-08-14 | 2015-12-09 | 上海银天下科技有限公司 | Service record compliance checking method and device |
| GB201705519D0 (en) * | 2016-04-05 | 2017-05-17 | Chase Information Tech Services Ltd | A secure searchable media object |
| CN107424640A (en) * | 2017-07-27 | 2017-12-01 | 上海与德科技有限公司 | A kind of audio frequency playing method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610718A (en) * | 2017-08-29 | 2018-01-19 | 深圳市买买提乐购金融服务有限公司 | A kind of method and device that voice document content is marked |
| CN108287930A (en) * | 2018-03-08 | 2018-07-17 | 珠海格力电器股份有限公司 | Recording search method and device and electronic equipment |
-
2018
- 2018-08-15 CN CN201810927508.4A patent/CN109241334A/en active Pending
- 2018-12-24 WO PCT/CN2018/123067 patent/WO2020034538A1/en not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011053563A (en) * | 2009-09-03 | 2011-03-17 | Neikusu:Kk | Collation system of voice keyword in voice data, method thereof, and collation program of voice keyword in voice data |
| CN105141787A (en) * | 2015-08-14 | 2015-12-09 | 上海银天下科技有限公司 | Service record compliance checking method and device |
| GB201705519D0 (en) * | 2016-04-05 | 2017-05-17 | Chase Information Tech Services Ltd | A secure searchable media object |
| CN107424640A (en) * | 2017-07-27 | 2017-12-01 | 上海与德科技有限公司 | A kind of audio frequency playing method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750230A (en) * | 2019-09-30 | 2020-02-04 | 北京淇瑀信息科技有限公司 | A voice interface display method, device and electronic device |
| CN112101311A (en) * | 2020-11-16 | 2020-12-18 | 深圳壹账通智能科技有限公司 | Double-recording quality inspection method and device based on artificial intelligence, computer equipment and medium |
| CN112509609A (en) * | 2020-12-16 | 2021-03-16 | 北京乐学帮网络技术有限公司 | Audio processing method and device, electronic equipment and storage medium |
| CN112509609B (en) * | 2020-12-16 | 2022-06-10 | 北京乐学帮网络技术有限公司 | Audio processing method and device, electronic equipment and storage medium |
| CN116092528A (en) * | 2022-12-30 | 2023-05-09 | 沈阳即时智能科技有限公司 | Audio quality inspection method and system |
| CN116092528B (en) * | 2022-12-30 | 2025-11-21 | 沈阳即时智能科技有限公司 | Audio quality inspection method and system |
| CN116346987A (en) * | 2023-04-18 | 2023-06-27 | 平安国际融资租赁有限公司 | A real-time audio quality inspection method and device, storage medium, and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020034538A1 (en) | 2020-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241334A (en) | Audio keyword quality detecting method, device, computer equipment and storage medium | |
| US10529336B1 (en) | Filtering sensitive information | |
| US7995732B2 (en) | Managing audio in a multi-source audio environment | |
| US11971926B2 (en) | Audio file quality and accuracy assessment | |
| CN110351443A (en) | Intelligent outgoing call processing method, device, computer equipment and storage medium | |
| CN109102797A (en) | Speech recognition test method, device, computer equipment and storage medium | |
| CN109815489A (en) | Collection information generation method, device, computer equipment and storage medium | |
| US20140160224A1 (en) | Tracking participation in a shared media session | |
| CN108766418A (en) | Sound end recognition methods, device and equipment | |
| US20160189713A1 (en) | Apparatus and method for automatically creating and recording minutes of meeting | |
| KR102548365B1 (en) | Method for generating conference record automatically and apparatus thereof | |
| US20160189103A1 (en) | Apparatus and method for automatically creating and recording minutes of meeting | |
| CN111835985B (en) | Video editing method, equipment, device and storage medium | |
| US20160189107A1 (en) | Apparatus and method for automatically creating and recording minutes of meeting | |
| US20190027151A1 (en) | System, method, and computer program product for automatically analyzing and categorizing phone calls | |
| CN112235471B (en) | Call center work order processing method and device, computer equipment and storage medium | |
| CN111916110B (en) | Voice quality inspection method and device | |
| CN109101484A (en) | Recording file processing method, device, computer equipment and storage medium | |
| CN110298543B (en) | Service tracking method, device, computer equipment and storage medium | |
| CN110310127B (en) | Recording acquisition method, recording acquisition device, computer equipment and storage medium | |
| CN116049479B (en) | Playlist generation methods, media, devices and computing equipment | |
| CN110110099A (en) | A kind of multimedia document retrieval method and device | |
| KR20130090870A (en) | Listen and write system on network | |
| US11062693B1 (en) | Silence calculator | |
| CN113448950A (en) | Localized hardware deployment method based on data volume |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |
|
| RJ01 | Rejection of invention patent application after publication |