JPH0242238B2 - - Google Patents

Description

[Detailed Description of the Invention] <Technical Field> The present invention relates to an improvement of a syllable boundary selection method in a voice input device, and more specifically, to a voice input device that is capable of determining syllable boundaries according to the speaking rate. It is.

<Prior Art> In general, in a method of extracting and identifying syllables from continuously uttered speech, the accuracy of segmentation of the syllables greatly influences recognition performance.

Conventional segmentation methods have a problem in that the number of segmentation errors changes as the speaking speed changes. This is due to the fact that the segmentation algorithm is fixed regardless of the speaking speed.

<Purpose> The present invention has been made in view of the above points, and it estimates the speech rate of continuous speech and calculates the speech rate based on the estimated speech rate from among the syllable boundary candidates output from the syllable boundary detection section. It is an object of the present invention to provide a speech input device that determines syllable boundaries by selecting the syllable boundaries.

<Example> Hereinafter, the present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing the overall configuration of a voice input device embodying the present invention.

In FIG. 1, a voice analysis unit 1 extracts characteristic parameters such as power p(t) and spectrum y(t) from the voice signal at input time t. The characteristic parameters extracted in the speech analysis section 1 are input to the speech rate detection section 2, and the power of the parameters input by the silent section detection section 21 and the voiced section detection section 22 in the speech rate detection section 2 is input to the speech rate detection section 2. A sound section and a silent section are distinguished based on the strength of p(t).

Also, the speaking rate estimation unit 23 in the speaking rate detecting unit 2
The average syllable length L is estimated and output based on the duration of the voiced section of the speech input of a training sentence whose number of syllables is known.

That is, when using a voice input device, the user first utters a training sentence whose number of syllables is known, and the speech rate estimator 23 calculates the average syllable length (1/
The average speaking rate) will be estimated.

Now, let L(i) be the duration of the i-th voiced interval detected by the voiced interval detection unit 22 when a sentence containing n syllables is uttered (where i=1, 2,... , m), the average syllable length = 1/2 _n 〓 ⁱ⁼¹ L(i) is calculated and output in the speech rate estimation unit 23.

Based on the duration of the silent section detected by the silent section detection section 21, the phrase boundary detection section 3 detects when the duration of the silent section exceeds a predetermined length, and detects the silent section. is regarded as a bunsetsu boundary and outputs a message to that effect.

The syllable boundary detection unit 4 outputs syllable boundary candidates using the feature parameters extracted by the speech analysis unit 1, using the speech segmented into phrases by the phrase boundary detection unit 3 as a unit. The interval between is the syllable length). In this syllable boundary detection unit 4,
As shown in Figure 2, a syllable boundary was clearly detected at time t ₁ and time t ₃ , but it may be difficult to determine whether or not a syllable boundary exists at time t ₂ . In this case, the final determination of syllable boundaries is made by the syllable boundary selection unit 5.

The syllable boundary selection unit 5 determines a syllable boundary by comparing the syllable length of the syllable boundary candidate detected by the syllable boundary detection unit 4 with the average syllable length estimated by the speech rate estimation unit 23.

Now, in the example shown in Figure 2, if time t ₂ is not a syllable boundary, a syllable of length t ₃ - t ₁ (length of A1 in the figure) exists in the time domain t ₁ < t < t ₃ . If it is a syllable boundary, the length t ₂ −t ₁
(the length of B1 in the figure) and length t ₃ -t ₂ (the length of B2 in the figure), but the syllable boundary selection unit 5 selects these syllable length candidates A1, B1, B2
and the average syllable length to determine syllable boundaries. In the example shown in Figure 2, the length of A1 is longer than B.
Since it is closer to the average syllable length than the lengths of A1 and B2, the syllable of length A1 is selected and time _t2 is determined to be not a syllable boundary.

The syllable boundary selection algorithm carried out in the syllable boundary selection section 5 will be more generalized and explained below.

Now, as shown in FIG. 3, a certain time domain T ₁ <
At t<T ₂ , it is difficult to determine syllable boundaries, so
The syllable boundary detection unit 3 selects several syllable candidate sequences A,
Suppose that B, C, ... are created and output (however,
The syllable candidate string A has a length A1, A2, ..., Aa
(The same applies to syllable candidate sequences B, C, ...).

These syllable candidate strings A, B, C, ... are input to the syllable boundary selection section 5, and the deviations D A , D B , D C, ... of the syllable candidates _A , _B , _C , ... from the average syllable length are determined respectively. D _A =1/a _a 〓 ⁱ⁼¹ d(A(i),) D _B =1/b _b 〓 ⁱ⁼¹ d(B(i),) D _C =1/c _c 〓 ⁱ⁼¹ d (C(i),) where d(x,y)= |x−k ₁ y|if length x
There is a silent interval before the syllable of length x |x-k ₂ y|if There is a clause boundary after the syllable of length x |x-y|if Calculated as other than the above.

Here, since syllables and plosives that come at the beginning of a phrase are often shorter than the average syllable length, 0<k ₁ <
Since the syllable at the end of a phrase is often long, k ₂ >1 is set.

The syllable boundary selection unit 5 selects a syllable candidate sequence having the smallest deviation from the average syllable length among the deviations D _A , D _B , D _C , ... calculated as above from the average syllable length. output as a syllable string.

The syllable recognition unit 6 matches the syllable section obtained as described above with the syllable standard pattern stored in the syllable standard pattern memory 7, and outputs a recognition result.

In the above embodiment, when using the voice input device, the known training sentence is first uttered to calculate the average syllable length, but the present invention is not limited to this, and the present invention can be The average syllable length may be calculated and stored in advance for a plurality of speakers. It is also possible to calculate and store a plurality of average syllable lengths in states of fast, normal, and slow speech rates for the same speaker, and select the average syllable length depending on the speech state at the time of recognition.

<Effects> As explained above, according to the present invention, the speech rate is first estimated, and the syllable boundaries are determined based on the estimated speech rate, so that inputs due to speaker characteristics etc. Regardless of the difference in speech rate,
Syllable boundaries can be detected and determined accurately.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the configuration of a voice input device embodying the present invention, FIG. 2 is a diagram showing an example of a detected syllable boundary, and FIG. 3 is a diagram showing another example of detected syllable boundary candidates. It is a diagram. 1... Voice analysis section, 21... Silent section detection section, 22
...Speech interval detection unit, 23...Speech rate estimation unit, 3...
Bunsetsu boundary detection section, 4... syllable boundary detection section, 5... syllable boundary selection section.

Claims (1)

[Scope of Claims] 1. A speech rate estimator that calculates the average syllable length by dividing the sum of durations in voiced sections of speech whose utterance content is known by the number of syllables included in the speech; A syllable boundary detection unit that detects syllable boundaries, and the average syllable length calculated by the speech rate estimation unit for the plurality of syllable boundary candidates detected by the syllable boundary detection unit, and the similarity. A voice input device comprising: a syllable boundary selection unit that determines a candidate with the highest degree as a syllable boundary;