JP2018146901A - Acoustic analyzing method and acoustic analyzing apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To estimate a time sequence of a plurality of sound pieces configuring an acoustic signal, based on the acoustic signal.SOLUTION: An acoustic analyzing apparatus 100 estimates a time sequence of a plurality of sound piece signals Q configuring an acoustic signal S, by comparing each of N sound piece signals Q with the acoustic signal S. A correlation analyzing unit 22 calculates a cross-correlations of the sound piece signal Q and the acoustic signal S, in each of N sound piece signals Q. An estimation processing unit 24 estimates a time sequence of the plurality of sound piece signals Q configuring the acoustic signal S. The estimation processing unit 24 estimates the time sequence of the plurality of sound piece signals Q, so that an accumulated cross correlation for two or more sound piece signals Q is maximized, in a cross correlation of the sound piece signal Q and the acoustic signal S at an end of the two or more sound piece signal Q arranged on a time axis.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for analyzing an acoustic signal representing sound.

  Conventionally, an acoustic processing technique (for example, a voice synthesis technique of a recording and editing method) that synthesizes various acoustic signals by arranging a plurality of pieces of sound prepared in advance on the time axis has been proposed. For example, Patent Document 1 discloses a technique for generating synthesized speech by mutually combining a previously recorded sound piece and a speech generated by a rule synthesis process.

JP 2006-145691 A

  There is a scene where it is required to estimate the time series of a plurality of sound pieces applied to the synthesis of an acoustic signal from the synthesized acoustic signal. For example, in a scene where guidance voices of transportation such as trains are synthesized, various information corresponding to the utterance contents of the guidance voice is provided to the user by estimating a plurality of sound pieces constituting the synthesized acoustic signal. Service is realized. In view of the above circumstances, an object of the present invention is to estimate a time series of a plurality of sound pieces constituting an acoustic signal from the acoustic signal.

  In order to solve the above problems, an acoustic analysis method according to a preferred aspect of the present invention provides a plurality of sound pieces constituting the sound signal by comparing each of the N sound piece signals with the sound signal. Estimate the time series of the signal. The acoustic analysis device according to a preferred aspect of the present invention estimates a time series of a plurality of sound piece signals constituting the sound signal by comparing each of the N sound piece signals with the sound signal. An analysis processing unit is provided.

It is a lineblock diagram of an acoustic analysis device in a 1st embodiment of the present invention. It is explanatory drawing which shows the relationship between an acoustic signal and a several sound piece signal. It is explanatory drawing of the cross correlation of an acoustic signal and a sound piece signal. It is explanatory drawing of operation | movement of an estimation process part. It is a flowchart which illustrates operation | movement of an acoustic analyzer. It is a block diagram of the information provision apparatus in 3rd Embodiment.

<First Embodiment>
FIG. 1 is a configuration diagram of an acoustic analysis apparatus 100 according to the first embodiment of the present invention. The acoustic analysis device 100 is a signal processing device that analyzes an acoustic signal S representing voice, and is realized by a computer system including a control device 12 and a storage device 14. For example, various information processing apparatuses such as a mobile phone, a smartphone, or a personal computer can be used as the acoustic analysis apparatus 100.

  The control device 12 is configured by a processing circuit such as a CPU (Central Processing Unit), for example, and comprehensively controls the operation of the acoustic analysis device 100. The storage device 14 stores a program executed by the control device 12 and various data used by the control device 12. For example, a known recording medium such as a magnetic recording medium and a semiconductor recording medium can be used as the storage device 14. A combination of a plurality of recording media of the same type or different types configured separately from each other can be used as the storage device 14.

The storage device 14 of the first embodiment stores the acoustic signal S. As illustrated in FIG. 2, the acoustic signal S is a time-domain signal generated in advance by arranging a plurality of sound piece signals Q (Q _{1 to} Q ₃ ) in time series and interconnecting them. . The sound piece signal Q is a signal representing a waveform of a partial sound (hereinafter referred to as “sound piece”) that constitutes a speech sound. One sound piece is a sound that is generated by segmental units such as words, phrases, and phrases. FIG. 2 exemplifies an acoustic signal S representing a voice “soon to arrive on the first line” that guides the user to the arrival of the train. As illustrated in FIG. 2, the sound signal S includes a sound piece signal Q ₁ representing a sound piece “soon”, a sound piece signal Q ₂ representing a sound piece “on line 1”, and “a train is coming. composed of the vibrating bar signal Q ₃ representing the speech piece that ". The time length of each sound piece signal Q can be different.

  As understood from the above description, for example, the acoustic signal S is generated in advance by a recording and editing type speech synthesis technique in which a plurality of sound piece signals Q representing sound pieces recorded in advance are connected. By changing the arrangement (total number, combination, order) of the plurality of sound piece signals Q, acoustic signals S representing various utterance contents are generated. The arrangement of the plurality of sound piece signals Q constituting the acoustic signal S is unknown. The acoustic analysis device 100 according to the first embodiment estimates a time series of a plurality of sound piece signals Q constituting the acoustic signal S.

  The storage device 14 of the first embodiment stores a plurality (N) of sound piece signals Q representing different sound pieces. Each of the N sound piece signals Q is assigned a different number (hereinafter referred to as “sound piece number”). The sound piece number n (n = 1 to N) is identification information for identifying the sound piece signal Q. The N sound piece signals Q stored in the storage device 14 are used for the analysis of the acoustic signal S. In other words, the acoustic analysis device 100 according to the first embodiment compares each of the N sound piece signals Q stored in the storage device 14 with the acoustic signal S, so that a plurality of components constituting the acoustic signal S are compared. The time series of the sound piece signal Q is estimated.

  The control device 12 functions as an analysis processing unit 20 for estimating a time series of a plurality of sound piece signals Q from the acoustic signal S by executing a program stored in the storage device 14. A configuration in which the function of the control device 12 is distributed to a plurality of devices, or a configuration in which a dedicated electronic circuit realizes at least a part of the function of the control device 12 may be employed.

  The analysis processing unit 20 estimates the time series of the plurality of sound piece signals Q constituting the sound signal S by comparing each of the N sound piece signals Q stored in the storage device 14 with the sound signal S. To do. As illustrated in FIG. 1, the analysis processing unit 20 of the first embodiment includes a correlation analysis unit 22 and an estimation processing unit 24.

The correlation analysis unit 22 calculates the cross-correlation C _{t, n} between the sound piece signal Q and the acoustic signal S for each of the N sound piece signals Q stored in the storage device 14 for each unit period (frame). To do. The symbol t is a variable indicating any one unit period among a plurality (T) of unit periods obtained by dividing the acoustic signal S on the time axis (t = 1 to T). Specifically, the cross-correlation C _{t, n} between the sound piece signal Q of the sound piece number n and the acoustic signal S is expressed by the following formula (1).

A symbol X _{t in} Expression (1) is a frequency spectrum in the t-th unit period of the acoustic signal S. Symbol D _{n, t} in Equation (1) is a frequency spectrum in the t-th unit period in the sound piece signal Q of the sound piece number n. Each of the frequency spectrum X _t and the frequency spectrum D _{n, t} is expressed by a series of a plurality of numerical values corresponding to different frequencies (frequency bins) on the frequency axis, and is obtained by a known frequency analysis such as a short-time Fourier transform. Calculated.

The symbol L _{n in the} formula (1) is the time length of the sound piece signal Q of the sound piece number n. The symbol ￣ in the formula (1) means complex conjugate, and the symbol * in the formula (1) means a product for each element. Symbol F ^{−1 in} Equation (1) is an inverse discrete Fourier transform.

As understood from the above description, when the position on the time axis of the sound piece signal Q of the sound piece number n with respect to the sound signal S is changed, the waveform is similar between the sound piece signal Q and the sound signal S. The cross-correlation C _{t, n} at the time point t corresponding to the end of the sound piece signal Q becomes a larger numerical value. That is, as illustrated in FIG. 3, in the state where the sound piece signal Q is arranged so that the end coincides with the time point t at which the cross-correlation C _{t, n of the} sound signal S becomes maximum, The waveform of the sound piece signal Q is similar. In the acoustic signal S, a section extending from the time point t at which the cross-correlation C _{t, n} is maximized to the time length L _{n in the} reverse direction (the direction in which the time is retroactive) is similar to the waveform of the sound piece signal Q of the sound piece number n. In other words. As understood from the above description, the correlation analysis unit 22 of the first embodiment is expressed as an element that compares each of the N sound piece signals Q with the acoustic signal S.

As illustrated in FIG. 4, a time series (hereinafter referred to as “speech series”) Z of a plurality of sound piece signals Q connected to each other on the time axis is assumed. In FIG. 4, two sound piece sequences Z (Z ₁₂ , Z ₂₃ ) composed of a combination of two of the _three sound piece signals Q _{1 to} Q ₃ are shown for convenience. For each of the _three sound piece signals Q _{1 to} Q ₃ , the cross-correlation C _{t, n} (C _{t, 1} , C _{t, 2} , C _{t, 3} ) is also shown in FIG.

Now, as illustrated in FIG. 4, the cross-correlation C _{t, n} between the sound piece signal Q and the acoustic signal S at the end of each sound piece signal Q constituting the sound piece sequence Z is _expressed as the sound piece sequence Z. A numerical value (hereinafter referred to as “cumulative cross-correlation”) R that is accumulated for a plurality of sound piece signals Q that constitutes is considered.

For example, for the sound piece sequence Z _{12 in} which the sound piece signal Q ₁ is followed by the sound piece signal Q ₂ , the total value of the cross-correlation C _{ta, 1} and the cross-correlation C _{tb, 2} is calculated as the cumulative cross-correlation R _12. Is done. The cross-correlation C _{ta, 1} is a time t _a at the end of the sound piece signal Q ₁ in the sound piece sequence Z ₁₂ among the cross-correlations C _{1,1 to} C _{T, 1} between the sound piece signal Q ₁ and the acoustic signal S. It is a numerical value corresponding to. On the other hand, the cross-correlation _{C tb, 2,} the sound piece signal _{Q 2} and of the cross-correlation _C 1, 2 _{-C T, 2} the acoustic signal S, the speech piece signal _{Q 2} at the speech segment sequence _{Z 12} end point is a numerical value that corresponds to t _b.

As for the speech segment sequence _{Z 23} in which subsequent to cause the tuning bar signal _{Q 3} in the speech segment signal _{Q 2,} calculating the total value of the cross-correlation _{C tc, 2} and the cross-correlation _{C td, 3} as the cumulative cross-correlation _{R 23} Is done. The cross-correlation C _{tc, 2} is at the time t _c at the end of the sound piece signal Q ₂ in the sound piece sequence Z ₂₃ among the cross-correlations C _{1,2 to} C _{T, 2} between the sound piece signal Q ₂ and the acoustic signal S. Corresponding numerical value. The cross-correlation C _{td, 3} is the time t _d at the end of the sound piece signal Q ₃ in the sound piece sequence Z ₂₃ among the cross-correlations C _{1,3 to} C _{T, 3} between the sound piece signal Q ₃ and the acoustic signal S. Corresponding numerical value.

In FIG. 4, it is assumed that the acoustic signal S is actually composed of the sound piece signal Q ₁ and the sound piece signal Q ₂ (that is, the sound piece sequence Z ₁₂ is correct). Therefore, the cross-correlation _{C ta, 1} sound piece signal cross-correlation _{C tb} at the end of the time _{t b} of _{Q 2, 2} larger numbers at the end of the time _{t a} of the speech piece signal _{Q 1} at the speech piece series _{Z 12} ( (A value close to the maximum value 1). That is, the cumulative cross-correlation _{R 12} becomes large numbers. On the other hand, the cross-correlation C _{tc, 2} at the end time t _c of the sound piece signal Q ₂ in the sound piece sequence Z ₂₃ and the cross-correlation C _{td, 3} at the end time t _d of the sound piece signal Q ₃ are small numerical values. Become. That is, the cumulative cross-correlation _{R 23} is a smaller number.

  As understood from the above description, the closer the sound piece sequence Z is to the combination of the plurality of sound piece signals Q constituting the acoustic signal S, the larger the cumulative cross-correlation R calculated for the sound piece sequence Z becomes. . Therefore, the cumulative cross-correlation R can be used as an index for evaluating the suitability of the sound piece series Z. That is, as the cumulative cross-correlation R of the sound piece sequence Z is larger, it can be evaluated that the sound piece sequence Z is more appropriate as a combination of a plurality of sound piece signals Q constituting the acoustic signal S. Against the background described above, the estimation processing unit 24 estimates the sound piece series Z (the time series of the plurality of sound piece signals Q) so that the cumulative cross-correlation R is maximized.

  By the way, as a method of estimating the sound piece sequence Z that maximizes the cumulative cross-correlation R, the cumulative cross-correlation R is calculated for all permutations (speech sequence Z) in which a plurality of sound piece signals Q are arranged. A method of selecting a sound piece sequence Z that maximizes the cross-correlation R is also assumed. However, the amount of calculation may be enormous in the above method. Therefore, the estimation processing unit 24 according to the first embodiment searches for the sound piece series Z that maximizes the cumulative cross-correlation R by using dynamic programming that can make the estimation process more efficient. The specific operation of the estimation processing unit 24 will be described in detail below.

数式（２）のうち右辺の第１項は、時点ｔから音片番号ｎの音片信号Ｑの時間長Ｌ_ｎだけ遡及した時点(ｔ−Ｌ_ｎ)について算定されたＮ個の累積相互相関Ｒ_{ｔ−Ｌｎ，１}〜Ｒ_{ｔ−Ｌｎ，Ｎ}の最大値（ｍａｘ）である。推定処理部２４は、現在の時点ｔについて相関解析部２２が算定した相互相関Ｃ_ｔ，ｎを当該最大値に加算することで、累積相互相関Ｒ_ｔ，ｎを算定する。 Assuming that the end of the sound piece signal Q having the sound piece number n is located at the time t of the acoustic signal S, the cumulative cross-correlation R _{t, n} at the time t is expressed by the following equation (2). The cumulative cross-correlation R _{t, n in} Equation (2) is calculated for each of the N sound piece signals Q.

The first term on the right side of Equation (2) is the N cumulative cross-correlations calculated for the time point (t−L _n ) retroactive from the time point t by the time length L _n of the sound piece signal Q of the sound piece number n. It is the maximum value (max) of R _{t-Ln, 1 to} R _{t-Ln, N.} The estimation processing unit 24 calculates the cumulative cross-correlation R _{t, n} by adding the cross-correlation C _{t, n} calculated by the correlation analysis unit 22 for the current time t to the maximum value.

Further, the sound piece number It _{, n} of the sound piece signal Q that maximizes R _{t−Ln, m} in Expression (2) is expressed by Expression (3) below.

When the cumulative cross-correlation R _{1, n to} R _{T, n up} to the end of the acoustic signal S is calculated for each sound piece number n, the estimation processing unit 24 determines N at the end (t = t ₀ = T) of the acoustic signal S. A sound piece number n ₀ of the sound piece signal Q corresponding to the maximum value of the cumulative cross-correlations _{RT, 1 to RT, N} is selected. That is, the sound piece number n ₀ is expressed by the following mathematical formula (4).

The sound piece number n _{0 in} Equation (4) is the sound piece number n of the sound piece signal Q located at the end of the acoustic signal S. Speech segment number n ₁ of the speech piece signal Q to be located just before the speech piece signal Q of speech segment number n _0, as will be understood from the formula (3) is a speech segment number I _{t0, n0,} the immediately preceding time _{t 1} the end of the vibrating bar signal Q is the time of the retroactively from the time _{t 0} by the time length _{L n0} of the _{n 0} th speech unit signal Q _(t 0 _{-L n0).} As understood from the above description, the process (backtrack) of tracing the sound piece signal Q in the reverse direction from the end of the acoustic signal S is expressed by the recurrence formulas of the following formulas (5) and (6). .

The estimation processing unit 24 repeats the backtrack expressed by Expression (5) and Expression (6) until the start point of the acoustic signal S is reached. The time series (speech piece) of the plurality of sound piece signals Q constituting the acoustic signal S by the series {n _I , n _I−1 ,..., N ₁ , n ₀ } of the sound piece numbers n _i searched in the above procedure. A sequence Z) is represented.

FIG. 5 is a flowchart of an operation (hereinafter referred to as “acoustic analysis process”) in which the control device 12 of the first embodiment estimates the sound piece series Z. For example, the acoustic analysis process is started in response to an instruction from the user. When the acoustic analysis process is started, the correlation analysis unit 22 uses the cross-correlation C _{t, n} between the sound piece signal Q and the sound signal S as a unit for each of the N sound piece signals Q stored in the storage device 14. Calculation is performed for each period (frame) (S1). When the calculation of the cross-correlation C _{t, n} is completed, the estimation processing unit 24 estimates the sound piece sequence Z that maximizes the cumulative cross-correlation R by the above-described dynamic programming (S2).

As described above, in the first embodiment, the time series of the plurality of sound piece signals Q constituting the sound signal S is estimated by comparing each of the N sound piece signals Q with the sound signal S. It is possible. In particular, in the first embodiment, the numerical value (cumulative cross-correlation R) obtained by accumulating the cross-correlation C _{t, n} at the end time t of each sound piece signal Q over the time series of the plurality of sound piece signals Q is maximized. In addition, a time series (speech series Z) of a plurality of sound piece signals Q is estimated. Therefore, there is an advantage that the time series of the plurality of sound piece signals Q constituting the sound signal S can be estimated with high accuracy from the viewpoint of the waveform similarity between each sound piece signal Q and the sound signal S. In the first embodiment, the sound piece sequence Z is estimated by dynamic programming. Therefore, for example, after calculating the cumulative cross-correlation R for all permutations in which a plurality of sound piece signals Q are arranged, the control device is compared with a method of selecting a sound piece sequence Z that maximizes the cumulative cross-correlation R. The amount of computation by 12 can be reduced. However, a method of searching for the maximum value after calculating the cumulative cross-correlation R for all the permutations of the plurality of sound piece signals Q may be employed.

Second Embodiment
A second embodiment of the present invention will be described. In addition, about the element which an effect | action or function is the same as that of 1st Embodiment in each form illustrated below, the code | symbol used by description of 1st Embodiment is diverted, and each detailed description is abbreviate | omitted suitably.

In the first embodiment, since the sound signal S is formed by arranging a plurality of sound piece signals Q on the time axis without overlapping or gaps, the interval between the last two sound piece signals Q ( The interval between the time point t _i-1 and the time point t _i is _equal to the time length L _n of the sound piece signal Q. However, in practice, two adjacent sound piece signals Q may be arranged in a state where they overlap or are separated from each other. In other words, the end interval between the two adjacent sound piece signals Q (interval between the time point t _i-1 and the time point t _i ) is a time length slightly different from the time length L _n of the sound piece signal Q. There is a possibility. In consideration of the above circumstances, in the second embodiment, the error ε is added to the end interval between two adjacent sound piece signals Q, and a plurality of sound piece signals Q constituting the sound signal S are added. A time series (speech piece series Z) is estimated.

すなわち、数式（２ａ）における右辺の第１項は、時点ｔから音片番号ｎの音片信号Ｑの時間長Ｌ_ｎだけ遡及した時点(ｔ−Ｌ_ｎ)を中心として幅２Ｅの範囲内（ｔ−Ｌ_ｎ±Ｅ）におけるＮ個の累積相互相関Ｒ_{ｔ−Ｌｎ＋ε，１}〜Ｒ_{ｔ−Ｌｎ＋ε，Ｎ}の最大値（ｍａｘ）である。定数Ｅは所定の正数である。数式（２ａ）における累積相互相関Ｒ_{ｔ−Ｌｎ＋ε，ｍ}を最大化させる音片信号Ｑの音片番号Ｉ_ｔ，ｎは、以下の数式（３ａ）で表現される。すなわち、第１実施形態の数式（３）が第２実施形態では数式（３ａ）に置換される。

Specifically, in the second embodiment, the formula (2) of the first embodiment is replaced with the following formula (2a).

In other words, the first term on the right side in the formula (2a) is within the range of the width 2E around the time point (t−L _n ) retroactive by the time length L _n of the sound piece signal Q of the sound piece number n from the time point t ( This is the maximum value (max) of _N cumulative cross-correlations R _{t−Ln + ε, 1 to} R _{t−Ln + ε, N} at t−L _n ± E). The constant E is a predetermined positive number. The sound piece number I _{t, n} of the sound piece signal Q that maximizes the cumulative cross-correlation R _{t−Ln + ε, m} in Expression (2a) is expressed by Expression (3a) below. That is, Formula (3) in the first embodiment is replaced with Formula (3a) in the second embodiment.

Further, the error ε that maximizes the cumulative cross-correlation R _{t−Ln + ε, m} is expressed by the following equation (7).

数式（６ａ）から理解される通り、推定処理部２４は、時点ｔ_ｉ−１に対して音片信号Ｑの時間長Ｌ_ｎｉ−１だけ遡及した時点から更に誤差Ｊ_{ｔｉ−１，ｎｉ−１}だけずれた時点を時間軸上の逆方向に辿る。すなわち、推定処理部２４は、第１実施形態と同様の数式（５）と誤差Ｊ_ｔ，ｎを含む数式（６ａ）とで表現されるバックトラックにより、音片番号ｎ_ｉの系列｛ｎ_Ｉ，ｎ_Ｉ−１，…，ｎ_１，ｎ_０｝（音響信号Ｓを構成する複数の音片信号Ｑの時系列）を推定する。 The backtrack executed by the estimation processing unit 24 of the second embodiment is expressed by the following formula (6a) in which the error J _{t, n} of the formula (7) is introduced into the formula (6) of the first embodiment.

As understood from the mathematical expression (6a), the estimation processing unit 24 further increases the error J _{ti−1, ni−1} from the time point L _ni−1 retroactive to the time point t _i−1 . Traces the time point shifted in the opposite direction on the time axis. That is, the estimation processing unit 24, the same formula as in the first embodiment (5) the error _{J t,} the backtracking expressed out with equations (6a) containing _n, speech segment number _{n i} of sequence _{{n I} , N _I−1 ,..., N ₁ , n ₀ } (time series of a plurality of sound piece signals Q constituting the acoustic signal S) is estimated.

In the second embodiment, the same effect as in the first embodiment is realized. In the second embodiment, since the error ε is added to the time length L _n of each sound piece signal Q, even if two adjacent sound piece signals Q overlap or are separated from each other, the sound There is an advantage that the time series of the plurality of sound piece signals Q constituting the signal S can be estimated with high accuracy.

<Third Embodiment>
FIG. 6 is a configuration diagram of an information providing apparatus 200 using the acoustic analysis apparatus 100 of the first embodiment or the second embodiment. As illustrated in FIG. 6, the information providing apparatus 200 according to the third embodiment is realized by a computer system including a control device 32, a storage device 34, a sound collection device 36, and a sound emission device 38. Note that the information providing apparatus 200 can be realized as a single apparatus or a plurality of apparatuses configured separately from each other.

  The control device 32 is configured by a processing circuit such as a CPU, for example, and comprehensively controls the operation of the information providing device 200. The storage device 34 stores a program executed by the control device 32 and various data used by the control device 32. For example, a known recording medium such as a magnetic recording medium and a semiconductor recording medium can be used as the storage device 34. The storage device 34 of the third embodiment stores N sound piece signals Q exemplified in the above-described embodiments.

  The sound collection device 36 collects a guidance voice (hereinafter referred to as “guidance voice”) G that is sounded or broadcasted at various facilities such as a traffic facility or a commercial facility, so that an acoustic signal representing the guidance voice G is collected. S is generated. The guidance voice G represented by the acoustic signal S is a time series of a plurality of sound pieces. The sound emitting device 38 reproduces sound under the control of the control device 32.

  The control device 32 functions as a modulation processing unit 42 and a mixing processing unit 44 in addition to the analysis processing unit 20 exemplified in the first embodiment or the second embodiment by executing a program stored in the storage device 34. To do. A configuration in which the function of the control device 32 is distributed to a plurality of devices or a configuration in which a dedicated electronic circuit realizes at least a part of the function of the control device 32 may be employed. The analysis processing unit 20 estimates the sound piece sequence Z from the acoustic signal S generated by the sound collection device 36 by the configuration and operation exemplified in the first embodiment or the second embodiment. That is, the information providing apparatus 200 of the third embodiment is configured to include the acoustic analysis apparatus 100 of the first embodiment or the second embodiment. Therefore, also in the third embodiment, the same effect as the first embodiment or the second embodiment is realized.

  The modulation processing unit 42 generates a modulation signal M corresponding to the sound piece sequence Z estimated by the analysis processing unit 20. The modulation signal M is a signal including distribution information B corresponding to the sound piece series Z as an acoustic component. The distribution information B is identification information for identifying the sound piece sequence Z itself or the sound piece sequence Z, for example. The modulation processing unit 42 generates the modulation signal M by modulation processing such as frequency modulation for modulating a carrier wave such as a sine wave of a predetermined frequency with the distribution information B, or spread modulation of the distribution information B using a spread code. . The frequency band of the acoustic component of the distribution information B is, for example, a frequency band that can be reproduced by the sound emitting device 38, and a range that exceeds the frequency band of the sound that the user listens to in a normal environment (for example, 18 kHz or more and 20 kHz or less).

  The mixing processing unit 44 generates the acoustic signal Y by mixing (for example, adding) the acoustic signal S supplied from the sound collection device 36 and the modulation signal M generated by the modulation processing unit 42. The sound emitting device 38 emits the sound represented by the acoustic signal Y. That is, the guidance sound G represented by the acoustic signal S and the acoustic component of the distribution information B represented by the modulation signal M are reproduced from the sound emitting device 38. As understood from the above description, the sound emitting device 38 of the first embodiment functions as an acoustic device that reproduces the guidance voice G, and also distributes the distribution information B by acoustic communication using sound waves as air vibration as a transmission medium. It also functions as a transmitter to transmit.

  6 is an information terminal such as a mobile phone or a smartphone. Note that, for example, a display terminal for guidance such as an electronic bulletin board or an electronic signboard (for example, digital signage) can be used as the terminal device 300. The terminal device 300 according to the third embodiment demodulates the distribution information B from the reproduced sound by the information providing device 200, and outputs related information corresponding to the distribution information B from an output device (for example, a display device or a sound emitting device). The related information indicated by the distribution information B generated from the acoustic signal S of the guidance voice G is information related to the guidance voice G (for example, a character string representing the guidance voice G or a translation thereof). As understood from the above description, the user of the terminal device 300 can listen to the guidance voice G reproduced by the information providing apparatus 200 and can confirm related information corresponding to the guidance voice G by the terminal device 300. Is possible.

  In the above description, the distribution information B is transmitted to the terminal device 300 by acoustic communication. However, the communication method for transmitting the distribution information B is not limited to the above examples. For example, the distribution information B can be transmitted to the terminal device 300 by wireless communication (typically short-range wireless communication) using electromagnetic waves as a transmission medium. It is also possible to transmit the related information as the distribution information B to the terminal device 300.

<Modification>
Each aspect illustrated above can be variously modified. Specific modifications are exemplified below. Two or more modes arbitrarily selected from the following examples can be appropriately combined within a range that does not contradict each other.

(1) The sample value of the acoustic signal S may be thinned out at a predetermined ratio and then compared with each sound piece signal Q. According to the above configuration, the calculation amount of the control device 12 can be reduced.

(2) The sound piece number It _{, n in} Equation (3) or Equation (3a) and the error J _{t, n in} Equation (7) need to be held over the entire interval of the acoustic signal S, but are estimated processing At the stage where the unit 24 calculates the cumulative cross-correlation R _{t, n} at the time point t, the past cumulative cross-correlation R from the time point (t−L _max −ε) is unnecessary. The time length L _max is the maximum value of the time length L _n of the N sound piece signals Q. As understood from the above description, it is sufficient to store {(L _max + E) × N} accumulated cross-correlations R in the storage device 14 at an arbitrary time point t.

(3) In each of the above-described embodiments, the acoustic signal S representing the voice is exemplified, but the acoustic signal S representing the sound other than the voice (for example, a musical sound) is also processed by the same method as in each of the above-described embodiments. It is possible to estimate a time series of a plurality of sound piece signals Q that constitute. Therefore, the sound represented by each sound piece signal Q is not limited to sound. For example, by analyzing the sound signal S composed of a plurality of sound piece signals Q representing sound pieces extracted from different music pieces, the sound pieces (and music names) used as the material of the sound signal S are obtained. It is possible to specify.

(4) In the first embodiment and the second embodiment, the acoustic signal S stored in the storage device 14 is analyzed. However, as understood from the illustration in the third embodiment, the sound collection device collects sound. It is also possible to analyze the generated acoustic signal S.

(5) The acoustic analysis device 100 according to each embodiment described above is realized by the cooperation of the control device 12 and the program as illustrated in each embodiment. The program according to each of the above-described embodiments is obtained by comparing each of the N sound piece signals Q and the sound signal S with the control device 12 (exemplification of a computer), thereby a plurality of sound piece signals constituting the sound signal S. An acoustic analysis process for estimating a time series of Q (sound piece series Z) is executed.

  The programs exemplified above can be provided in a form stored in a computer-readable recording medium and installed in the computer. The recording medium is, for example, a non-transitory recording medium, and an optical recording medium (optical disk) such as a CD-ROM is a good example, but a known arbitrary one such as a semiconductor recording medium or a magnetic recording medium This type of recording medium can be included. Note that the non-transitory recording medium includes any recording medium except for a transient propagation signal (transitory, propagating signal), and does not exclude a volatile recording medium. It is also possible to provide a program to a computer in the form of distribution via a communication network.

(6) From the form illustrated above, for example, the following configuration is grasped.
<Aspect 1>
In the acoustic analysis method according to a preferred aspect (aspect 1) of the present invention, each of the N sound piece signals is compared with the sound signal, so that the time series of the plurality of sound piece signals constituting the sound signal is obtained. presume. According to the above configuration, by comparing each of the N sound piece signals with the sound signal, it is possible to estimate a time series of a plurality of sound piece signals constituting the sound signal.
<Aspect 2>
In a preferred example of aspect 1 (aspect 2), the time series estimation of the plurality of sound piece signals is performed by calculating a cross-correlation between the sound piece signal and the acoustic signal for each of the N sound piece signals. A correlation analysis and an estimation process for estimating a time series of the plurality of sound piece signals selected from the N sound piece signals. In the estimation process, two or more sound pieces arranged on a time axis A time series of the plurality of sound piece signals so that a cumulative cross-correlation of the sound signal and the sound signal at the end of the signal with respect to the two or more sound piece signals is maximized. Is estimated. In the above aspect, the time series of the plurality of sound signal is estimated so that the accumulated cross correlation obtained by accumulating the cross correlation at the end of each sound signal over the time series of the plurality of sound signal is maximized. The Therefore, there is an advantage that the time series of the plurality of sound piece signals Q constituting the sound signal can be estimated with high accuracy from the viewpoint of the waveform similarity between each sound piece signal and the sound signal.

<Aspect 3>
The acoustic analysis device according to a preferred aspect (aspect 3) of the present invention compares each of the N sound piece signals with the sound signal, thereby obtaining a time series of a plurality of sound piece signals constituting the sound signal. An analysis processing unit for estimation is provided. According to the above configuration, by comparing each of the N sound piece signals with the sound signal, it is possible to estimate a time series of a plurality of sound piece signals constituting the sound signal.

DESCRIPTION OF SYMBOLS 100 ... Acoustic analysis apparatus, 200 ... Information provision apparatus, 300 ... Terminal device, 12, 32 ... Control apparatus, 14, 34 ... Storage device, 20 ... Analysis processing part, 22 ... Correlation analysis part, 24 ... Estimation processing part, 36 ... sound collecting device, 38 ... sound emitting device, 42 ... modulation processing unit, 44 ... mixing processing unit.

Claims (3)

An acoustic analysis method for estimating a time series of a plurality of sound piece signals constituting the sound signal by comparing each of the N sound piece signals with the sound signal. Time series estimation of the plurality of sound piece signals is
For each of the N sound piece signals, a correlation analysis for calculating a cross-correlation between the sound piece signal and the acoustic signal;
An estimation process for estimating a time series of the plurality of sound piece signals selected from the N sound piece signals,
In the estimation process, a cross-correlation between the sound signal and the acoustic signal at the end of the two or more sound signal arranged on the time axis is accumulated for the two or more sound signals. The acoustic analysis method according to claim 1, wherein a time series of the plurality of sound piece signals is estimated so that the correlation is maximized. An acoustic analysis apparatus comprising: an analysis processing unit that estimates a time series of a plurality of sound piece signals constituting the sound signal by comparing each of the N sound piece signals with the sound signal.

Images