JPH09244687A - Speech recognizing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To carry out highly precise speech recognition making good use of environment-dependent phoneme standard patterns. SOLUTION: While a network is generated by utilizing context free grammar having an environment-dependent phoneme as a termination symbol and an LR(land reserve) purser, a standard pattern is determined and while an input speech is matched against standard patterns of HMM(hidden markov model) a one-pass search is advanced; and environment-dependent phoneme standard patterns as used as the standard patterns of HMM and when an environment- dependent phoneme P3 is predicted by the LR purser from a tip node 3 at the time of the extension of the network, tracing from a new node 4 back to the last node is performed to set the environment-dependent phoneme standard patterns to the arc between nodes 3 and 4 by using phoneme strings P1 , P2 , and P3 as a triphone model.

Description

Detailed Description of the Invention

[0001]

TECHNICAL FIELD The present invention relates to a hidden Markov model (for example, Seiichi Nakagawa “Speech Recognition by Probabilistic Model” edited by The Institute of Electronics, Information and Communication Engineers (1988)) and a generalized LR context analysis algorithm (for example, M. Tomita: " An Efficient Context-F
ree Parsing Algorithm for Natural Languages and it
s Applications ”, Carnegie-Mellon University (198
5)) and the One-Pass search algorithm (eg J. Br.
idle and others: "An Algorithm For Connected Word Recogni
, ICASSP82, pp. 899-902 (1982)) and a method for continuously recognizing input speech.

[0002]

2. Description of the Related Art In conventional speech recognition, an LR parser (grammar analyzer) is used to search for a recognition candidate that meets a predetermined grammar, and recognition is performed while matching a standard pattern of the recognition candidate with an input speech. There is a way to do. In addition, using a predetermined network, the standard pattern is collated with the input voice for a part of it, and the search is advanced while minimizing the increase in the processing amount except for those with a small score, and finally the score is obtained. One-Pass search method is known in which the highest candidate of is the recognition result.

Furthermore, a method of speech recognition is known in which a hidden Markov model, a generalized LR parser, and a One-Pass algorithm are integrated. As this integrated recognition method, a sub-network is created from the context-free grammar with environment-independent phonemes using the LR parser, and the environment-dependent phonemes are considered at the junctions between these sub-networks to determine the environment-dependent phoneme standard. From methods using patterns (for example, Katsutoshi Ito: “Continuous Speech Recognition Using Extended LR Parsing Method”, IEICE Technical Report, SP90-74, pp. 49-56) and context-free grammars using environment-independent phonemes. There was a method to dynamically create one network using a parser and use the phoneme standard pattern independent of environment. (For example, Kenji Kita et al .: "L
One-Pass continuous speech recognition algorithm by R parser control ", IEICE Tech., SP94-13 (1994-
05) 55-62).

From the viewpoint of efficiency, it is better to process with one network without using the sub-network, and from the viewpoint of accuracy of speech recognition, it is better to use the environment-dependent phoneme standard pattern, but both are used at the same time. There was no way I could do it.

[0005]

SUMMARY OF THE INVENTION The present invention integrates a Hidden Markov Model, a generalized LR parser, and a One-Pass algorithm, efficiently processes them using a single network, and at the same time, uses environment-dependent phoneme standard patterns. It is an object of the present invention to provide a voice recognition method that can utilize the above and has a high recognition rate.

[0006]

According to the present invention, by using the environment-dependent phoneme standard pattern, the network is traced back to the newly generated node on the network by the number of phonemes taking the phoneme environment into consideration. The set of environment-independent phonemes predicted by the LR parser is specified, and the environment-dependent phoneme standard pattern to be set in the arc connected to the node is determined.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 functionally shows the structure of a recognition device to which an embodiment of the present invention is applied. The voice input from the input terminal 1 is converted into a digital signal in the feature extraction unit 2 and further subjected to LPC cepstrum analysis, and then 1
It is converted into a feature parameter every frame (for example, 10 milliseconds). This feature parameter is, for example, an LPC cepstrum coefficient.

An environment-dependent phoneme standard pattern of a hidden Markov model is created from the learning speech database in the same format as the above-mentioned feature vector and stored in the standard pattern memory 4. From the context-free grammar that defines the range of the recognition target and uses the environment-independent (environment-independent) phonemes as terminal symbols,
A table for the R parser is created and stored in the LR table 5.

FIG. 2 shows a flowchart of the processing in the recognition section 3.
Shown in The characteristic parameters of the input speech for one frame are read (S ₁ ), the network is grown (every frame or every several frames) (S ₂ ), and pattern matching between the input speech characteristic parameters and the standard pattern is performed (S 1).
₃ ) Then, in the next step, the active node to be processed is determined and the process returns to step S ₁ (S ₄ ). This is repeated until there is no input voice. Even if the input voice does not disappear, the process may be terminated under some condition from the score obtained by the pattern matching.

The network consists of nodes and arcs, initially there is only one initial node. Each node is a hypothesis generated by using the LR parser, and one having the same stack contents is assigned and associated. Therefore, LR parsers that perform the same processing thereafter are integrated into the same node (arcs are connected to the same node). Here, this is called a merge node. Based on the collation result in each step, the one with a high score is set as an active node to be processed in the next step. Other nodes may be retained in the network as they are, or may be discarded for effective use of memory. In this way, the One-P is extended while expanding the network by using the context-free grammar and the LR parser, which are environment-independent phoneme termination signals.
We will proceed with the search by the ass search.

The generation (growth operation) of the network, which is a characteristic part of the present invention, will be described with reference to FIG. Since a network of infinite size can be created from the context-free grammar, it is assumed that the entire network cannot be created in advance. So in the network generator,
The operation of creating a new node from each active node of the network using the LR parser and extending the arc (growing the network) is limited to a finite number of phonemes ahead. Here, a case where one phoneme is extended at a time will be described. In the figure, the symbols shown above the dotted lines are environment-independent phonemes predicted between the nodes by the LR parser. A solid line between the nodes is an arc of the network. In the present invention, an environment-dependent phoneme standard pattern is set (1-2, 2-3, in order to make the diagram easy to see).
Arcs between nodes 5-6 and 6-3 are omitted). Here, the so-called triphon, which takes into consideration the environment on the left side (L) and the right side (R) of the central phoneme (C).
This will be described in the case of the e model and will be referred to as LCR.

First, a simple case of FIG. 3A will be described. Consider a case where the network is grown for the node 3 from the network in which the nodes 1 to 3 have been generated. It is assumed that the LR parser predicts the phoneme P ₃ independent of the environment from the node 3 and changes it to the state of the stack represented by the new node 4. Here, by tracing back from the node 4 to the node three nodes before, a three-phoneme sequence of P ₁ , P ₂ , and P ₃ is obtained. Based on this, an environment-dependent phoneme standard pattern of P ₁ -P ₂ -P ₃ is set in the arc between the nodes 3-4.

Diagram of the case where node 3 is a merge node
3B will be described. In this case, the node three nodes before node 4
By tracing back to the node, P₁
−P _Two−P_ThreeAnd P_Four−P_Five−P_ThreeThe two arcs that set
I find it necessary. And ensure the acoustic consistency
To keep node 3 split into two or node 2
P for those arcs₁−P_Two−P_ThreeIs the arc from node 6
For P_Four−P_Five−P_ThreeAnd the data will be passed
So that there are restrictions.

In order to reduce the processing amount, it is possible to consider a method that does not consider consistency. In this case, the result obtained contains an error. Finally, on the LR parser
The pt) hypothesis becomes one merge node. At the end of all steps, the recognition result can be obtained by tracing back the arc that propagated the highest score to this merge node. The environment dependence of phonemes is not limited to the triphone model, but the number of phonemes in the phoneme environment-dependent model of the standard pattern is made equal to the number of phonemes going back in the network when the network is expanded.

[0015]

EFFECT OF THE INVENTION Suppose that an environment-dependent phoneme is a terminal symbol.
When the R table is used, the number of merge nodes is small and the syntax is the same, but the network grows while being divided into a plurality of paths, that is, a large number of paths are generated, that is, a large number of candidates are generated, and a large amount of computation is required. Become. However, in the present invention, the merge node which is distributed when the LR table having the environment-dependent phonemes as the terminal symbols is dispersed is avoided by using the LR table having the environment-independent (environment-independent) phonemes as the terminal symbols. Moreover, the required number of arcs and nodes from the merge node are traced to determine the environment-dependent phoneme standard pattern,
Since it is set to the arc of the newly created node, it is possible to perform highly accurate recognition processing using environment-dependent phoneme standard patterns while dynamically creating a network with high merge efficiency.

[Brief description of drawings]

FIG. 1 is a block diagram showing a functional configuration example of a recognition device to which a method according to an embodiment of the present invention is applied.

FIG. 2 is a flowchart of a recognition processing unit showing an embodiment of the present invention.

FIG. 3 is a diagram illustrating a method of setting an environment-dependent phoneme standard pattern in an arc of a network in an embodiment of the present invention.

Claims (1)

[Claims] 1. A phoneme standard pattern is determined while generating a network by using an LR parser and a context-free grammar whose input speech is a characteristic parameter time series and environment-independent phonemes are terminal symbols. One-while checking the characteristic parameter time series and the standard pattern of the hidden Markov model
In a speech recognition method in which a search is advanced by a Pass search and a candidate having a high similarity likelihood is used as a recognition result, an environment-dependent phoneme standard pattern is used as the standard pattern of the hidden Markov model, and when the network is expanded, A speech recognition method characterized in that an environment-dependent phoneme standard pattern is determined by tracing back the network from the tip by the number of phonemes taking the environment dependence into consideration and an arc on the network is set.