JPH0568717B2 - - Google Patents

Description

[Detailed Description of the Invention] (Technical Field) The present invention relates to a speech recognition method, and more specifically, the present invention relates to a speech recognition method, and specifically, a speech recognition method in which a recognition operation is started from detecting the beginning of input speech without waiting for confirmation of the end of word input speech. Regarding recognition methods.

(Background Art) As a form of speech recognition method, a standard pattern is stored as a frame time series of frequency components corresponding to each standard voice, and the input pattern is extracted from the input speech as a frame time series of frequency components. A known method is to calculate the degree of dissimilarity between an input pattern and each standard pattern, and to identify input speech based on the degree of dissimilarity.

For example, Oki Research and Development No. 118, page 53, Showa
It was disclosed in December 1957. In such a method, the standard or input speech pattern is usually frequency-analyzed by setting frames regularly, and then subjected to logarithmic transformation and normalization of vocal fold vibration characteristics using a least squares approximation straight line, and then the frequency components are determined. , expressed as a frame time series.

In addition, methods for setting matching paths to calculate the degree of dissimilarity between the input pattern and each standard pattern include the DP matching method using dynamic programming and the essentially linear matching method as seen in the above-mentioned literature. The law is known. From the perspective of simplifying the configuration, the linear matching method is advantageous, but
As illustrated in Figure 1, the utterance speed of a word varies extremely widely, with individual differences as well as changes depending on the psychological state and situation. There is some variation in the results, and some kind of improvement is required. Various types of linear matching methods have been proposed, but not only in the above-mentioned literature, in which a matching path is set after detecting the end of input speech, there are problems in terms of recognition response, and there are It is also necessary to memorize the starting point until the ending point is confirmed.

(Objective of the Invention) An object of the present invention is to increase the recognition speed by detecting the beginning of the input voice and immediately starting the matching operation, and by setting the matching path in anticipation of variations in the speaking rate. The purpose is to absorb fluctuations in speaking speed.

(Summary of the Invention) The first feature of the present invention is that matching processing is performed for each frame of the input pattern, and the degree of dissimilarity corresponding to each matching pass of each standard pattern is updated and stored for each frame. It is in.

First, a method using audio power can be used to detect the presence of audio. In this case, the start end of the audio is detected when the frame power P(j) (where j is the frame number of the input pattern) exceeds a predetermined threshold. However, due to external noise or the like, the power P(j) may exceed the threshold value even if no voice input is being performed, and the starting point may be incorrectly determined. Therefore, although the frame whose frame power P(j) exceeds the threshold is considered to be the starting point and recognition processing is started, if the frame power exceeds the threshold for three or more consecutive frames, the input frame is not considered to be the starting point of the audio. The recognition process is interrupted and the process returns to the start edge detection process. However, the frame length
It is set to 16 msec. Here, the numbering of the frame whose frame power exceeds the threshold from the start of the audio is defined and is called the h-th audio frame, which is distinguished from a simple input frame number. That is, the audio frame with audio frame number h corresponds to the h-th input frame in the voiced period.

If the matching process that normalizes the speech rate can be started from the beginning of the voice and performed every cycle (frame period) in which the output of the voice analyzer is obtained, there is no need to store all the data from the voice analyzer from the start. , and the reaction time is also faster.

A second feature of the present invention is to set matching paths assuming cases in which utterances are performed slowly, normally, and quickly, and perform matching processing on each matching path. At the time of detecting the beginning of speech, the speech rate of the word that is about to be input is unknown. Therefore, by setting matching paths assuming that the utterance is performed slowly, normally, or quickly, and performing matching processing on each matching path, matching processing can be started even before the end is detected. becomes. Of course, in this case, there is a small possibility that there exists a path where the end of the input matches the end of the standard pattern, but the dissimilarity on the path where the end of the input most matches the end of the standard pattern is minimal. It is expected that

On the other hand, some words have a portion where the frame power is less than the threshold, such as between the "i" and "chi" in "ichi", that is, a silent frame. This part is called the "power dip." The length of this power dip varies depending on the word, but it usually rarely exceeds 30 frames. After detecting the start of audio, if the frame power at a certain frame time point is less than the threshold, that is, the frame becomes silent, it is difficult to determine whether that frame time point is the beginning of a power dip or the end of audio. This determination is usually made from that point onwards.
This is done depending on whether there is a frame that satisfies the audio start condition (3 or more frames in a row where the frame power is above the threshold) within 30 frames, so a decision cannot be made until 30 frames have passed at most. Therefore, the matching results when the frame power becomes less than the threshold must be suspended in some way. In the present invention, this problem is solved by stopping the updating of the audio frame number and stopping the matching process for frames whose frame power is less than a threshold value, that is, in a silent state.

FIG. 2a is a diagram showing an example of a plurality of matching passes for matching an input pattern and a standard pattern in the speech recognition method according to the present invention, FIG. 2b is a diagram showing an example of frame power of the input pattern,
Figure 2c shows the dissimilarity Dn(j), D′n(j), in each matching pass between the input pattern and the standard pattern,
FIG. 3 is a diagram showing an example of D″n(j).

In Figure 2 a, the range of speech rate is, for example, ±
The figure shows the case where three matching paths are set, assuming that the ratio is 20%. In FIG. 2a, the horizontal axis represents the frame number of the input pattern. Further, the vertical axis represents the frame number of the standard pattern, and taking the nth standard pattern Sn as an example, let its frame length be SL(n). Reference numeral 101 indicates a path assuming that the speech is uttered 20% slower, 102 a path that assumes standard speech, and 103 a path that assumes that the speech is uttered 20% faster. When the power of the j-th input frame is greater than or equal to the threshold, the distance from the standard pattern Sn on the three paths is given by the following equation. However, h
is the audio frame number corresponding to the j-th input frame number, and W(i, j) is when the input frame number is j and the channel number is i (where i = 1 to 8).
Sn (i, k) is a component of the standard pattern with frame number k and channel number i.

Distance to path 101 dn(j)= ₈ 〓 ⁱ⁼¹ |W(i,j)−Sn(i,k)|
...Equation 1, where k = [1/1.2h] [1/1.2h]≦SL(n) SL(n) [1/1.2h]>SL(n) Distance to path 102 d′n(j)= ₈ 〓 ⁱ⁼¹ | W (i, j) − Sn (i, k′) |
...Second formula where k'=h SL(n) h≦SL(n) h>SL(n) Distance to path 103 d″n(j)= ₈ 〓 ⁱ⁼¹ | W(i, j)−Sn (i, k″) |
...Third formula where k″=[1/0.8h] [1/0.8h]≦SL(n) SL(n) [1/0.8h]>SL(n) Note that [ ] indicates a Gaussian symbol.

According to the above equation, in path 101, the distance between the j-th input audio frame of the input pattern and the k-th frame of the standard pattern is calculated.
In pass 102, the distance between the j-th input frame of the input pattern and the k'-th frame of the standard pattern is calculated, and in the pass 103, the distance between the j-th input frame of the input pattern and the k''-th frame of the standard pattern is calculated. However, if k, k', k'' indicating the frame number of the standard pattern is larger than the length SL(n) of the standard pattern, it is limited to SL(n).

On the other hand, if the power of the j-th input frame is less than the threshold, the distances dn(j), d′n on each path
(j), d″n(j) are forced to dn(j)=0…4th equation d′n(j)=0…5th equation d″n(j)=0…6th equation As a result, processing is performed in which the dissimilarity calculation when the frame power is less than the threshold value is not actually added. For this purpose, the standard pattern is also stored in a form excluding frames corresponding to power dips, that is, frames corresponding to the silent state.

In this way, although the distance is set to 0 for frames that are not important as dissimilarities, such as power dips or matching after the end of a standard pattern, the matching is essentially linear in the present invention.

Next, the dissimilarities Dn(j), D′n(j), and D″n(j) of the input pattern up to the j-th input frame are calculated.

Dissimilarity of path 101 Dn(j)=dn(j)+Dn(j-1) ...Equation 7 Dissimilarity of path 102 D'n(j)=d'n(j)+D'n(j- 1) ...Equation 8 Dissimilarity of path 103 D″n(j)=d″n(j)+D″n(j−1) ...Equation 9 In other words, the j-th frame on each path The dissimilarity is calculated by dividing the distance for each channel (for example, |W (i, j) - Sn (i, k) 1)). These operations are performed when the j-th frame is input. When calculating the dissimilarity for the j-th input frame,
The input pattern data of the th frame, the standard pattern data corresponding to each pass, and 1
Only the dissimilarity data of the j-1th input frame before the frame is necessary, and the input pattern data of two or more frames before is unnecessary. Therefore,
This method also has the effect of reducing the storage area compared to the linear expansion/contraction matching method in which input patterns must be stored until the end is detected.

Figure 2c shows the dissimilarity Dn(j), D′n(j),
D″n(j), but as shown in Figure 2c, by forcing the distance value to 0 when the frame power is below the threshold, the dissimilarity Dn
(j), D′n(j), and D″n(j) are retained. Therefore, the dissimilarity at the end and the input frame 30 frames from the end (the end is detected for the first time at this point) The dissimilarities at are equal.

Next, the category is determined based on the degree of dissimilarity obtained for each standard pattern from the time when the end of the audio is detected (30 frames after the end of the audio). The input frame number at the time of end detection is J,
Letting the audio frame number be H, the dissimilarity of each path to the nth standard pattern is Dn(J), D′n(J),
It is given by D″n(J). There are as many sets of these dissimilarities as there are standard patterns (assumed to be N). Category determination is performed using these dissimilarities.
In other words, find the minimum value for all of the dissimilarities Dn(J), D′n(J), and D″n(J) found for each standard pattern. The selected category becomes the recognition result.

(Embodiment) FIG. 3 is an embodiment showing a circuit configuration for performing matching processing and determination processing in the present invention.
The operation will be explained in detail below.

In Fig. 3, reference numeral 52 is an audio frame counter that counts the number of audio frames from the start edge, and when the start edge is detected, its content becomes 0 by the reset pulse 50, and is input thereafter when the power of the input frame exceeds the threshold. A count up operation is performed by the count pulse 51. If the power of the input frame is less than the threshold, the count pulse 51 is not added and the output of the audio frame counter 52 is held. Let h be the audio frame number output from the audio frame counter 52. 53 is a signal representing the type of several paths during matching, and since the number of paths is three, it takes a value from 0 to 2. 54 is a ROM that gives frame numbers of the corresponding standard pattern on each path in the h-th audio frame.
The ROM 54 stores values corresponding to [1/0.8h], h, and [1/1.2h]. The output of ROM54 is
shall be. 55 is a standard pattern number signal which gives the number of the standard pattern, and is assumed to be n. When the total number of standard patterns is N, it takes a value from 0 to N-1. 56
is a ROM that stores the length SL(n) of the nth standard pattern. 57 is a ROM 54 that outputs the standard pattern frame number l.
output and the standard pattern length SL(n)
This is a comparator that compares the contents of the ROM 56 and outputs "1" if l≦SL(n), and outputs "0" if l>SL(n). A selector 58 selects the output of the ROM 54 when the output of the comparator 57 is "1", and selects the output of the ROM 56 when the output of the comparator 57 is "0". Comparator 57
According to the selector 58, if 1≦SL(n), then l is
If l>SL(n), an operation is performed in which SL(n) is output from the selector 58. The output of selector 58 is k
shall be. 59 is a signal giving channel number i. 60 is addressed by the channel number i, the output of the selector 58, for example k, and the standard pattern number signal n, and each component Sn of the standard pattern is
This is a standard pattern memory that outputs (i, k). Reference numeral 61 denotes a memory for storing each component W(i, j) of an input pattern for one frame which has undergone spectrum normalization, and is given an address by a channel number signal 59. 62 is an input terminal of the memory 61, which receives input data W(i,j) whose spectrum has been normalized by a spectrum normalization unit (not shown).
is input. 63 is the output W(i,
j) and the output Sn (i, k) of the standard pattern ROM60
This is an arithmetic unit that outputs the following values according to the control signal CONT between

When CONT = 1 When CONT = 0 |W (i, j) - Sn (i, k) | 0 ...Equation 13 CONT signal is "1" when the frame power is above the threshold, and when it is below the threshold is a signal that becomes "0". 64 is an adder, and 65 is an address that uses the values of the pass signal 53 and standard pattern number signal 55.
It is a RAM and stores dissimilarities Dn(j), D′n(j), and D″n(j). 70 compares the dissimilarity that is the output of the RAM 65 and the output of the register 71, which will be described later. This is a minimum value selection circuit that outputs two signals.
One is a signal that gives the smaller value of the comparison results, and this signal is stored in the register 71. The other signal is a clock that is generated if the output of RAM 65 is smaller as a result of the comparison, and becomes the input clock of register 72. Register 71 is a register that provides the minimum value of dissimilarity, and the maximum value of dissimilarity is set at the beginning of a frame period. The register 72 is a register that stores a standard pattern number signal based on the output pulse of the minimum value selection circuit 70, and stores the number of the standard pattern that gives the minimum value of dissimilarity. 73 is an output terminal.

FIG. 3 is constructed as described above, and its operation will be explained below.

Each process is started when the frame power p(j) becomes equal to or greater than the threshold value, but the process is reset unless the frame power P(j) is equal to or greater than the threshold value for three or more consecutive frames. The counter 52 is in the reset state by the reset pulse 50 before the start frame of the audio. Also, all values in the memory 65 have been reset. Hereinafter, the processing within one frame period after the start edge detection will be sequentially explained. However, for the sake of explanation, the input frame number is assumed to be j. If the frame power of the jth input frame exceeds the threshold, a count pulse 51 is applied to the counter 52;
2 counts up and outputs the audio frame number h. The standard pattern frame number corresponding to the audio frame number is output by ROM 54, ROM 56, comparator 57, and selector 58. The i-channel data Sn (i, k) of the k-th frame of the n-th standard pattern is stored in the ROM60.
is output by . On the other hand, input data W(i, j) after spectral normalization of the j-th input frame outputted from the previous-stage spectral normalization unit (not shown) is input to the memory 61 from the input terminal 62 and stored therein. There is. ROM60 output Sn(i,
k) and the output W(i, j) of the memory 61 are outputted in synchronization with the channel number signal 59, and the arithmetic unit 63 performs the calculation given by equation (13). Calculations corresponding to the first to ninth expressions are executed between the output of the arithmetic unit 63 and the memory 65. Actually, formulas 1 to 9
The expression operations are performed in the following unified form.

(Memory 65)←(Memory 65) +|W(i,j)−Sn(i,k)|0 Next, the minimum value selection circuit 70 selects the register 71.
The smaller of the dissimilarity stored in the RAM 65 and the dissimilarity output from the RAM 65 is stored in the register 71. At the same time, if the output of the RAM 65 is smaller, a pulse is applied to the register 72 and the standard pattern number at that time is stored in the register 72. If this process is performed for all standard patterns, the standard pattern number giving the minimum dissimilarity at that time will be stored in the register 72.

The above processing is performed for each frame period, and the result of the register 72 at the time when the end is detected becomes the final recognition result, and is outputted through the output terminal 73.

Note that even when the standard pattern number is the same, if the path signals are different, the degree of dissimilarity corresponding to each path will be different.
It can be exceeded.

(Effects of the Invention) As described above, the present invention has the advantage that the recognition result is obtained within one frame after the termination is detected because distance calculation and dissimilarity calculation are performed for each input frame. Furthermore, in order to calculate the dissimilarity, it is only necessary to accumulate the dissimilarity value for the previous input frame with the distance value for the current input frame, and there is no need to store input data from the start to the end.

Furthermore, since it is a method aimed at simplifying the circuit configuration, it is easy to implement on an LSI, and it can be realized by providing an inexpensive LSI chip for speech recognition with a small number of gates, and at the same time by using software processing on a general-purpose microprocessor. It's something you get.

[Brief explanation of drawings]

Figure 1 is a diagram for explaining utterance length variation, Figure 2
The figure is a diagram shown to explain the outline of the matching path of the present invention, and FIG. 3 is a block diagram showing an embodiment of the present invention. 52...Counter of audio frame number h, 54
...ROM for generating something equivalent to the frame number of the standard pattern, 56...ROM storing the length of the standard pattern, 57...comparator, 58...selector, 60...memory for the standard pattern, 61...Input pattern memory, 63...
... Distance calculator, 64 ... Adder, 65 ... RAM for storing dissimilarity, 70 ... Minimum value selection circuit, 7
1...Memory of minimum dissimilarity, 72...Memory of standard pattern number as recognition result.

Claims (1)

[Claims] 1. A standard pattern expressed as a frame time series of frequency components corresponding to each standard voice and expressed in a form in which frames corresponding to a silent state are removed is stored, and (a) input Extract the input pattern from the audio as a frame time series of frequency components, (b) Detect the start of the input audio and start counting the frames of the input pattern, and keep the audio frame number while detecting the active state. The audio frame number is updated sequentially, and while a silent state is detected, updating of the audio frame number is stopped, and when a sound state is detected again before the end of the input audio is confirmed, updating of the audio frame number is resumed, ( c) creating multiple matching passes between the input pattern and each standard pattern by generating multiple frame numbers of the standard pattern in an essentially linear relationship to that audio frame number for each update of the audio frame number; (d) Every time the audio frame number is updated, calculate the distance between the input pattern and each standard pattern between the frames associated with each matching pass, and (e) calculate the distance between the input pattern and each standard pattern from the start of the input audio. The accumulated value of the distance along the matching path up to the number is taken as the dissimilarity, and each time the audio frame number is updated, the immediately preceding dissimilarity and the distance at the frame number are added and temporarily stored. Therefore, the degree of dissimilarity corresponding to each matching pass for each standard pattern is updated and stored, and (f) the code of the standard pattern corresponding to the degree of dissimilarity showing the minimum value among all the degrees of dissimilarity is updated and stored in the voice. (g) When the end of the input audio is confirmed, the dissimilarity value corresponding to the minimum value stored corresponding to the audio frame number at the end of the input audio is updated and stored each time the frame number is updated. A speech recognition method characterized by recognizing standard pattern codes as categories of input speech.