JPH0336439B2 - - Google Patents

Description

[Detailed Description of the Invention] [Summary] In a continuous speech recognition device, a plurality of standard patterns are divided into first half and second half word standard patterns,
Continuous DP matching is performed on the first half word standard pattern of the speech input pattern, reverse time continuous DP matching is performed on the second half word standard pattern, and the results are limited by a certain threshold, and each frame of the input pattern is compared to the above. Select a standard pattern as the boundary of each half-word standard pattern, perform reverse time DP matching on the center candidate given by the standard pattern from the frame where the candidate is located in the direction of the start end,
DP matching is performed in the terminal direction, and DP processing is performed to minimize the sum of partial section matching distances for each given candidate to obtain a recognition result.

[Industrial application field]

The present invention is a continuous speech recognition device that recognizes speech in which multiple words are uttered continuously, and in particular recognizes continuous speech using dynamic programming (hereinafter referred to as DP), efficiently and with a high recognition rate. This paper relates to a continuous speech recognition device that has been improved so that it can be used in a long time.

[Conventional technology]

Various methods have been proposed for recognizing continuous speech formed by continuously uttering a plurality of words, and the following methods are typical.

The first method divides continuous words that form continuous speech into individual words using characteristics such as a drop in voice power at the boundaries of each word (this operation is called segmentation). This method recognizes each word by comparing it with a standard pattern.

The second method is a method in which all sets of sections of continuous words are extracted and compared with a standard pattern, and an optimal combination of sections is determined and recognized from the matching results.

[Problem that the invention seeks to solve]

Among the continuous speech recognition methods, the above-mentioned first method has problems in that it is very difficult to segment continuous words and it is difficult to ensure a high recognition rate.

On the other hand, the second method achieves a high recognition rate, but the amount of calculation is much larger than the first method.
There was a problem that continuous speech recognition with fast response time was not possible.

Furthermore, since the joined part of each word in continuous speech is easily deformed due to the influence of the words before and after it, it is difficult to specify its position accurately. For this reason, DP
An error occurs in the end candidate or start end candidate for each frame of the audio input pattern found by matching,
There was a problem that the recognition rate decreased.

Therefore, in order to solve these problems, multiple standard patterns are divided into half-word standard patterns for the first half and second half, and continuous DP matching is performed on the voice input pattern for the first half word standard pattern, and the second half word standard pattern is Perform inverse time continuous DP matching on Perform inverse time DP matching on candidates from the frame where the candidate is located in the direction of the starting edge,
A continuous speech recognition device (hereinafter referred to as the original invention) that performs DP matching in the terminal direction and obtains a recognition result by performing DP processing such that the sum becomes the minimum from the partial interval matching distance for each given candidate. Proposed by the same applicant.

This original invention selects the center candidate by continuous DP matching, which can significantly reduce the amount of calculation, and also extracts standard pattern candidates for each word in the stable part (for example, the center part). As a result, candidates can be found correctly and a high recognition rate can be obtained.

However, since there is always a center candidate for each frame, the number of center candidates increases, and even if the matching distance is large and it cannot be a valid center candidate, a center candidate is always selected for each frame, so the following There was a problem in that the effect of reducing the amount of calculations was lost due to increased processing waste.

It should be noted that since the content of the original invention and the content of the invention of the present application have many parts in common, they will be appropriately explained in connection with the embodiments of the present invention in the description of the embodiments below.

By limiting the frames of the input pattern in which the center candidate exists, the present invention further reduces the amount of calculations and improves processing efficiency than the original invention, which significantly reduces the amount of calculations compared to the conventional method. The purpose of this invention is to provide a continuous speech recognition device with response time.

[Means for solving problems]

The means taken by the present invention to solve the above-mentioned problems in the conventional continuous speech recognition device will be explained with reference to FIG.

FIG. 1 is a block diagram illustrating the configuration of the present invention.

In FIG. 1, 110 is a standard pattern dictionary section in which standard patterns of a plurality of spoken words are stored. When reading, each standard pattern is divided into a first half word standard pattern for the first half word and a second half word standard pattern for the second half word.

120 is a half-word continuous DP matching unit that performs matching (continuous
DP matching) is performed, and the input pattern is matched using inverse time continuous dynamic programming (inverse time continuous DP matching) for each second half word standard pattern among a plurality of standard patterns.

130 is the central candidate limited selection part, half word consecutive
From the results of the DP matching unit 120 limited to minimum values, for each frame of the input pattern, a standard pattern is found that makes that frame the boundary of each standard pattern of the first half word and the second half word, and a central candidate is selected from the standard pattern. do.

Reference numeral 140 is a word start/end level DP processing unit that performs matching by inverse time dynamic programming (inverse time DP matching) from the frame in which the center candidate is located in the direction toward the start end, and also performs matching (inverse time DP matching) by dynamic programming in the direction toward the end. DP matching) to find the subinterval matching distance.

Reference numeral 150 denotes a sentence level DP processing unit, which calculates the combination that minimizes the sum of the subsection matching distances for each digit of the input pattern based on the subsection matching distances input from the word start/end level DP processing unit 140. Based on the results, it is determined how many digits the input pattern contains, and a recognition result is obtained.

Note that "digit" expresses the positional relationship of each word, and each word of a continuous word is expressed as the first digit, second digit, . . . xth digit from the beginning.

[Effect]

The operation of FIG. 1 will be explained with reference to FIGS. 2 and 3.

Figure 2 is an explanatory diagram of continuous DP matching and inverse time continuous DP matching between the input pattern and each half-word standard pattern before and after, and examples of their matching routes. time dp
It is an explanatory diagram of collation.

In the case of continuous word speech, as mentioned above, the joined part of each word is easily deformed due to the influence of the adjacent words before and after it, so it is difficult to specify its position accurately, so DP An error occurs in the end or start end candidates for each frame of the input pattern found through matching, reducing the recognition rate.

Therefore, in the case of continuous word speech, the beginning and end of each word are easily deformed due to the influence of the words before and after it, but the center part is less affected by the words before and after it. Focusing on stability, the standard pattern candidates for each word in continuous speech are extracted from the stable portion of that word.

A plurality of standard patterns are stored in the standard pattern dictionary section 110, but when read out,
Divide each standard pattern into two half words, the first half and the second half.
The first half word standard pattern for the first half word and the second half word standard pattern for the second half word are read out.

In the method of dividing each standard pattern into half words, the first half and the second half, the central part is generally stable, so it is divided into two at the central part, but it is also possible to divide it into two at a stable part other than the central part.

As shown in FIG. 2, the half-word continuous DP matching unit 120 performs continuous DP matching on each of the first half word standard patterns of a plurality of standard patterns of the input pattern, and performs inverse time continuous DP matching on each second half word standard pattern. I do. Then, the continuous DP matching distance and the inverse time continuous DP matching distance, which are the matching results, are output.

The central candidate limited selection unit 130 selects half-word continuous DP
Based on the cumulative results of the continuous DP matching distance and the inverse time continuous DP matching distance inputted from the matching unit 120, which are limited to minimum values, each frame of the input pattern is compared to the first half and second half of the half-word standard pattern. A standard pattern is found as the boundary of , and a center candidate is selected from that standard pattern.

As a result, the number of center candidates is limited, and those that can be valid center candidates are selected.
The amount of subsequent calculations can be greatly reduced.

As shown in FIG. 3, for each center candidate selected by the center candidate limited selection section 130, the word start/end level DP processing section 140 extracts the start end from the frame in which the center candidate is located (indicated by k). Reverse time DP matching is performed in the direction, and DP matching is performed in the end direction to find the starting end center matching distance and the center ending matching distance, respectively. Next, a partial section matching distance is determined based on both matching distances.

The sentence level DP processing unit 150 finds a combination that minimizes the sum of the subsection matching distances for each digit of the input pattern based on the subsection matching distances input from the word start/end level DP processing unit 140, and calculates the combination that minimizes the sum of the subsection matching distances for each digit of the input pattern. The recognition result is determined by determining how many digits the input pattern contains.

As described above, center candidates are obtained by continuous DP matching, and subinterval candidates are selected by limiting the center candidates to the minimum value. Therefore, all subinterval combinations are extracted from the input pattern and multiple standard It is possible to significantly reduce the amount of calculation and obtain a faster response time than the conventional method (the above-mentioned second method) in which subsection candidates are found by matching patterns, as well as the original invention.
In addition, we extracted standard pattern candidates for each word in continuous speech from stable parts of that word.
Candidates can be found correctly and a high recognition rate can be ensured.

〔Example〕

An embodiment of the present invention will be described with reference to FIGS. 2 to 9.

Fig. 4 is an explanatory diagram of the configuration of an embodiment of the present invention, Fig. 5 is an explanatory diagram of DP verification with fixed start and end ends, Fig. 6 is an explanatory diagram of continuous DP verification, and Fig. 7 is an explanatory diagram of reverse time continuous DP verification. FIG. 8 is an explanatory diagram of the continuous DP calculation method, and FIG. 9 is an explanatory diagram of the center candidate frame limiting operation and the center candidate selection operation. 2 and 3 are as already explained.

(A) Configuration of the embodiment In FIG. 4, the standard pattern dictionary section 11
0, the half-word continuous DP matching unit 120, the central candidate selection unit 130, the word start/end level DP processing unit 140, and the sentence level DP processing unit 150 are as described in FIG.

In the half-word continuous DP matching unit 120, 12
1 is a continuous DP matching unit that performs continuous DP matching on each first half word standard pattern of a plurality of standard patterns to obtain a continuous DP matching distance (Gf (k, n)). 122 is backward time continuous
The DP matching section performs reverse time continuous DP matching on each of the second half word standard patterns of the input pattern to obtain a reverse time continuous DP matching distance (Gb (k, n)).

In the center candidate limited selection unit 130, 131
is the central candidate frame limited part, and half-word continuous DP
The cumulative values of the continuous DP matching distance Gf (k, n) and the inverse time continuous DP matching distance Gb (k, n) input from the continuous DP matching unit 120 are normalized, and the value (DS (k, n)) is The frame that takes the minimum value is the frame to be selected as the center candidate. 1
32 is a central candidate selection unit that selects the normalized cumulative half-word continuous DP from the limited frames.
A frame with the minimum matching distance DS (k, n) is found, and a standard pattern centered on that frame is selected as a center candidate.

In the word start/end level DP processing unit 140,
Reference numeral 141 denotes an inverse time DP matching unit, for each center candidate input from the center candidate limited selection unit 130,
Reverse time DP matching is performed in the direction of the starting edge from the frame where the center candidate is located to find the starting edge center matching distance (Gs (k, l)). Reference numeral 142 denotes a DP matching unit, which performs DP matching for each center candidate in the direction of the end from the frame in which the center candidate is located to obtain a center-end matching distance (Ge (k, m)).
Reference numeral 143 denotes a partial section candidate selection unit, which selects the start end center matching distance Gs (k, l) and the center end matching distance Ge.
(k, m) based on subinterval matching distance (D
(l, m)) and the corresponding standard pattern (Ns(l, m))
Find m)).

In the sentence level DP processing unit 150, 151
is the sentence level DP matching part, and the word start/end level DP
The standard pattern Ns(l, m) corresponding to the subsection matching distance D(l, m) input from the processing unit 140 is
m) to find the optimal combination of words by DP matching. A recognition result processing unit 152 determines how many digits the input pattern contains based on the result of the sentence level DP matching unit 151 to obtain a recognition result.

160 is a microphone; 170 is a voice feature extraction unit that extracts the features of the input continuous voice and converts it into an input pattern for verification; and 180 is an input pattern buffer in which this input pattern is stored.

(B) Operation of the embodiment The microphone 160 extracts continuous speech consisting of continuous words uttered by the user from the speech feature extraction unit 17.
Enter 0. The audio feature extraction unit 170 extracts the features of the input continuous audio, converts it into an input pattern for matching, and stores it in the input pattern buffer 18.
Store at 0.

The audio input pattern A at this time is expressed as follows.

A=a(1),a(2),a(3),...a(m)...a() Here, a(m) is a parameter in frame m, for example, when the frequency direction is divided into 16 channels. , is a vector quantity expressed by a power spectrum value in each section. The last I is the end frame of input pattern A and means the word length of input pattern A. Note that a frame is a voice section (more accurately, a voice section cut out using a window function).

Similarly, the standard pattern of the standard pattern dictionary section 110 is expressed as follows, where B(n) is the standard pattern of word n.

B(n) = b(1, n), b(2, n)...b(j,
n)...b(J(n), n) Here, b(j, n) is a parameter of word n in frame j, and similarly to input pattern A, it is expressed by, for example, the power spectrum value of 16 channels. It is a vector quantity. J(n)
is the final frame of word n and represents the word length of standard pattern B(n).

In the present invention, half-word matching is performed using continuous DP matching and reverse time continuous DP matching for the first half word standard pattern and the second half word standard pattern of the input pattern. This process is called word center level DP.

(B-1) Operation of continuous DP matching unit 121 In normal DP matching, the start and end of the input pattern are fixed, and as shown in Figure 5, one optimal matching path passing through the start and end is given. Then, the matching distance of the route is determined.

On the other hand, continuous DP matching, as shown in FIG. 6, refers to DP matching that is free from the start and ends at any frame of the input pattern. As a result, the optimal corresponding section existing in the input pattern A is automatically extracted, and the continuous DP matching distance is determined. Based on this result, it can be easily determined whether the standard pattern B(n) is likely to exist in the input pattern A, and if so, which frame of the input pattern A should be the end.

(B-2) Operation of the backward time continuous DP matching section 122 The backward time continuous DP matching performed by the backward time continuous DP matching section 122 performs continuous DP matching on the input pattern A in the reverse time direction, as shown in FIG. It is something to do. This determines whether standard pattern B(n) is likely to exist in input pattern A, and
If it is likely to exist, it is easy to determine which frame of input pattern A should be the starting point.

There are various methods of continuous DP calculation performed in the above-mentioned continuous DP matching and inverse time continuous DP matching, depending on how to take the matching path, etc., but here we will use a symmetric type as shown in Figure 8. do.

In FIG. 8, if the distance between the vectors of the standard pattern B and the input pattern A on the grid point (i, j) is d(i, j), then the matching distance gf(i, j ) is required.

When j = 1, gf (i, j) = gf (i, 1) = d (i, 1) When i = 1, j > 1, gf (1, j) = d (1, j) + gf (1,j-
1) When j > 1, gf (i, j) = mind (i, j) + gf (i-1, j) 2d (i, j) + gf (i-1, j-1) d (i, j )+gf(i,j-1) This gf(i,j) is the one that minimizes the sum of distances from point (1,1) to point (i,j).

Reverse time continuous DP matching is a method in which the input pattern is reversed and continuous DP matching is performed in the reverse time direction.
The calculation method is the same as the calculation method used during continuous DP verification described above, so the explanation will be omitted.

Through this continuous DP matching and reverse time continuous DP matching, the first half section and the second half section of standard pattern B are respectively matched as shown in FIG.

Let Gf(k) be the continuous DP matching distance on k frames of the input pattern, and let Gb(k) be the inverse time continuous DP matching distance. Furthermore, this Gf(k) and Gb
(k) is Gf for N standard patterns.
(k, n) and Gb (k, n), and the continuous DP matching unit 121 and the inverse time continuous DP
Each is output from the matching unit 122.

(B-3) Operation of the central candidate frame limiting unit 131 Gf (k, n) and Gb (k, n) input from the half-word continuous DP matching unit 140 are expressed by the following equation in the central candidate frame limiting unit 130. are accumulated to produce a cumulative half-word consecutive DP matching distance DC(k,n).

DC (k, n) = Gf (k, n) + Gb (k, n) DC (k, n) is a short one depending on the individual word length J (n) of the standard pattern B (n) as it is. Since the value tends to become smaller, time normalization is performed by dividing the value of DC(k, n) by the sum of each pattern length of input pattern A and standard pattern B(n). This time normalized
When DC (k, n) is expressed as DR (k, n),
DR(k,n) is expressed by the following formula.

DR (k, n) = DC (k, n) / 2J (n) The reason for using 2J (n) here is that if input pattern A is correctly matched with standard pattern B (n), the corresponding input This is because the pattern length is considered to take a value close to J(n). If you use some method to
Starting point L(k,n) for l,m of (k,n)
DR(k, n) can be obtained by the following equation when the terminal M(k, n) is known.

DR (k, n) = DC (k, n) / {J (n) + M (k, n) - L (k, n) + 1} This DR (k, n) is as shown in Figure 9. ,
A different distance pattern is shown for each n.

The original invention includes a half-word continuous DP matching unit 12.
The processing up to 0 is the same as in the present invention, but the ninth
DR the N distance patterns in the figure for each k
Select the smallest (k, n) value and
Candidate whose center is k frame (center candidate)
has been selected. For this reason, as described above, the number of center candidates increases, and even those that cannot be valid center candidates are selected, resulting in a correspondingly large amount of calculations, resulting in the inconvenience that a quick response time cannot be obtained.

In contrast, in the present invention, as shown in FIG.
When DR (k, n) takes a minimum value, it is assumed that there is a high possibility that the frame is the center frame of the standard pattern, and the frame is selected as a center candidate. If the minimum value is not taken, the frame is considered unlikely to be the center frame of the standard pattern, and is not included in center candidate selection. Thereby, the amount of calculation in each subsequent process can be significantly reduced.

The DR(k,n) of frames limited to those having minimum values in this manner is sent to the center candidate selection unit 132 as DS(k,n).

(B-4) Operation of center candidate selection unit 132 The center candidate selection unit 132 uses DS(k,n) input from the center candidate frame limiting unit 131.
Find the minimum value for n from
Select n as a candidate centered on frame k (center candidate), and set its standard pattern number to NC(k).

If there is no candidate, NC(k) is set to "0" so that it can be distinguished from the central candidate.

Through the above processing, the number of standard patterns B(n) centered on frame k of input pattern A is limited to one.

(B-5) DP verification unit 142 and reverse time DP verification unit 1
41 operation (word start/end level DP) The center candidate indicated by NC(k) is
DP matching by 42 and inverse time DP matching unit 14
By inverse time DP matching using 1, the starting and ending DP
Find the matching distance.

There are various DP calculation methods used here depending on how to take matching paths, etc., but here, a symmetric type is used like the continuous DP described above. That is, when i=1, j=1: ge(1,1)=d(1,1) When i=1, j>1: ge(1,j)=d(1,j)+ge( 1,j-1) When i>1, j=1: g(i,1)=d(i,1)+ge(i-1,j) When i>1, j>1: ge(i , j) = mind (i, j) + ge (i-1, j) 2d (i, j) + ge (i-1, j-1) d (i, j) + ge (i, j-1) This ge (i, j) is the minimum sum of distances from the grid point (1, 1) to the (i, j) point.

The DP matching distance ge(i,
j) is found, but the one at the end of the standard pattern is
Let it be Ge(i).

In addition, the inverse time DP matching distance gs(i, j) simply inverts the pattern and matches it,
The calculation method is the same as that for the DP matching distance ge(i,j), so the explanation thereof will be omitted. Let Gs(i) be the starting edge of the standard pattern.

Through these DP matching and reverse time DP matching,
The matching distance in the direction of the end and start end of the word center candidate NC(k) is determined.

Figure 3 shows the reverse time from the frame where the center candidate is located (indicated by k) in the direction of the starting point.
This is an example in which DP verification is performed, DP verification is performed in the direction of the end, and the start frame l and end frame for that frame are determined. Note that H(NC(k)) is the word length of the standard pattern of the central candidate.

Let the center-end matching distance obtained by the DP matching unit 142 by DP matching be Ge(k, m), and
The starting end center matching distance obtained by the inverse time DP matching unit 141 by the inverse time DP matching is expressed as Gs(k,l)
shall be.

(B-6) Operation of the partial section candidate selection section 143 The partial section candidate selection section 143 selects the input
The cumulative value of Ge (k, m) and Gs (k, l) is time-normalized by dividing it by the sum of the partial pattern length (ml+1) and the standard pattern length J (NC(k)). Letting the DP matching distance of this time-normalized subinterval be DI (k, l, m),
It is determined by the following formula. That is, DI (k, l, m) = Ge (k, m) + Gs (k, l)/J
(NC(K)))+m−l+1 Next, the partial section candidate selection unit 143 selects this
Select the minimum value of DI(k, l, m) for k and set it as D(l, m), and set the corresponding standard pattern to NS(l, m).

D(l,m)=min k {DI(k,l,m)} NS(l,m)=NC[argmin k {DI(k,l,m)} Here, “argmin k” is { This operator has the function of selecting k that satisfies the minimization condition within }.

If m has no terminal candidate, NS
Set "0" to (l, m) and set the maximum value to D(l, m).

By this D(l,m) and NS(l,m), the partial pattern (l-m) of the input pattern
The optimal matching distance (D(l, m)) and matching partner (NS(l, m)) are determined and output from the partial section candidate selection unit 143.

(B-7) Operation of the sentence level DP matching unit 151 The sentence level DP matching unit 151 uses the D input from the word start/end level DP processing unit 140.
Using (l, m) and NS (l, m), find the optimal combination of words by DP matching.

Here, each word in the continuous word is 1 from the beginning.
The positional relationship will be expressed using expressions such as digit, second digit, and so on.

(b) Setting the 1st digit The 1st digit is the distance of the partial section of m frames from the start frame of the input pattern, T(m,
l). That is, T (m, 1) = D (1, m) Also, set where the beginning of the standard word is in LT (m, 1). That is, LT (m, l) = 1 Here, D where there is no subinterval candidate
No processing is performed for (1, m), and NT
Set "0" to (m, 1) and the maximum value to T(m, 1).

(b) Setting the xth digit In the xth digit, the position of l is undetermined, so the next
Determined by the DP recurrence formula. That is, T(m,x) l<m= min l [D(l,m)+T(l,x-1)] NT(m,x) l<m=NS[ argmin l {D(l,m ) +T(l,x-1)},m] LT(m,x) l<m= argmin l [D(l,m) +T(l,x-1)] In this case too, D(l,m) If there is no subinterval candidate for and m, no processing is performed, and NT(m,
x) is set to the maximum value, and LT(m, x) is set to "1" (although an indefinite value is fine).

(B-8) Operation of recognition result processing unit 152 The recognition result processing unit 152 uses T(m,x) and NT sent by the sentence level DP matching unit 151.
T(m,x) in (m,x) and LT(m,x)
First, the number of digits X of the input word is found from the following equation.

X=argmin x [T(I,x)/x] where I is the terminal frame of the input pattern.

Next, the recognition result processing unit 152 obtains the recognition result of X digits from LT (m, x) and NT (m, x) using the following (a) and (b). Here, let NR(x) be the recognition result of x digits, and let L(x) be the starting frame of NR(x).

(b) Recognition result of X-th digit NR (x) = NT (I, X) L (x) = LT (I, X) (b) Recognition result of X-y-th digit NR (X-y) = NT [L(X-y+1),
X-y] L(X-1)=LT[L(X-y+1),X
−y] In the above manner, the recognition result NR(x) is
This can be determined with a significantly smaller amount of calculation and a higher recognition rate than in the past.

[Effects of the Invention] As explained above, according to the present invention, the following effects can be obtained.

(b) Since the central candidate is determined by continuous DP matching and the partial interval candidates are selected, the amount of calculation can be significantly reduced compared to the conventional method.

(b) Since candidates for the standard pattern of each word are extracted from the stable part of that word, candidates can be found correctly and a high recognition rate can be ensured.

(c) Since the frames in which the center candidate exists are limited, the amount of calculation in subsequent processing can be reduced and a fast response time can be achieved.

[Brief explanation of the drawing]

Fig. 1: An explanatory diagram of the configuration of the present invention; Fig. 2: An explanatory diagram of continuous DP matching of the first half word standard pattern and reverse time continuous DP matching of the second half word; and an explanatory diagram of an example of their matching route; Fig. 3: Word-centered An explanatory diagram of DP matching and reverse time verification in the terminal and starting end directions of candidates, FIG. 4...An explanatory diagram of the configuration of an embodiment of the present invention, FIG. 5...An explanatory diagram of DP matching with a fixed starting and ending end, FIG. 6 ...Explanatory diagram of continuous DP matching, Fig. 7...Explanatory diagram of reverse time continuous DP matching, Fig. 8...Explanatory diagram of continuous DP calculation method, Fig. 9
Figure: An explanatory diagram of a center candidate frame limiting operation and a center candidate selection operation. 1 and 4, 110... standard pattern dictionary section, 120... half word continuous DP matching section, 1
30... Central candidate limited selection section, 140... Word start/end level DP processing section, 150... Sentence level DP processing section.

Claims (1)

[Claims] 1. A speech feature extraction unit converts speech in which a plurality of words are continuously uttered into an input pattern, compares the input pattern with a plurality of standard patterns, selects candidates for each section, and In a continuous speech recognition device that obtains recognition by finding the one with the minimum matching distance between intervals, (a) the input pattern is matched by continuous dynamic programming for each first-half word standard pattern among multiple standard patterns; , a half-word continuous DP matching unit 120 that performs matching of the input pattern using inverse time continuous dynamic programming for each second-half word standard pattern among a plurality of standard patterns; (b) a result of the half-word continuous DP matching unit 120; A central candidate limited selection unit 130 that determines a standard pattern in which each frame of the input pattern is defined as a boundary between the standard patterns of the first half word and the second half word from those limited by the minimum value, and selects the central candidate from the standard pattern. (d) Perform matching using inverse time dynamic programming from the frame in which the center candidate is located in the direction toward the starting end, and perform matching using dynamic programming in the direction toward the end to find the subinterval matching distance at the word start/end level.
DP processing unit 140; (d) Find a combination that minimizes the sum of subinterval matching distances for each digit of the input pattern based on the subinterval matching distance, and determine how many digits the input pattern is from the result. A continuous speech recognition device comprising: a sentence level DP processing unit 150 that determines a recognition result.