This paper describes the method and the system investigated to solve the problem encountered in the automatic recognition of speech sound. From research in the automatic analyzer of speech sound, a monosyllable recognition system was constructed in which the phoneme is used as the basic recognition unit. Recently this system has been developed to accept the conversational speech sound with unlimited vocabulary. The mechanical recognition of conversational speech sound requires two basic operations. One is the segmentation of the continuous speech sound into several discrete intervals (or segments), each of which may be thought to correspond to a phoneme, and the other is the pattern recognition of such segments. For segmentation, by defining two criteria, ``stability'' and ``distance,'' the properties of the time pattern obtained by the analysis of input speech sound may be examined. The principle of the recognition is based on the mechanism of the articulation in our speech organ. Corresponding to this, the machine has the functions called phoneme classification, vowel analysis and consonant analysis. A conversational speech recognition system with the phonetic contextual approach is also applied to the vowel recognition where the time pattern of input speech is matched with the stored standard patterns in which the phonetic contextual effects are taken into consideration. The time pattern which has great variety may be effectively expressed by the new representation of ``sequential pattern'' and ``weighting pattern.''

The Automatic Speech Recognition System for Conversational Sound

Presents a categorized bibliography of heuristic search research materials gathered largely from the artificial intelligence (AI) literature. The intent is to provide an introduction to this information for researchers and practitioners in operations research. >

A bibliography of heuristic search research through 1992

Speaker-independent continuous-speech recognition by phoneme-based word spotting and time-synchronous context-free parsing☆

In this survey, we will provide a short survey and classification on the current work in special purpose architectures to support AI applications. In spite of the growing importance of AI applications, work in the area of designing AI architectures are so diversified that articles were published in other areas besides Al, ranging from psychology, medicine, manufacturing, computer architecture, software engineering, and database management to industrial engineering, operations research, and the list grows. The literature search is also complicated by the fact that with the development of the Fifth-Generation Computer Systems, some work in this area is very recent and was published in many foreign countries. During our literature search to compile this survey, we systematically went through over sixty different journals published in various countries and proceedings from over fifty conferences in the last twenty years and over seventy books.

A survey on special purpose computer architecture for AI

In this survey, we will provide a short survey and classification on the current work in special purpose architectures to support AI applications In spite of the growing importance of AI applications, work in the area of designing AI architectures are so diversified that articles were published in other areas besides Al, ranging from psychology, medicine, manufacturing, computer architecture, software engineering, and database management to industrial engineering, operations research, and the list grows The literature search is also complicated by the fact that with the development of the Fifth-Generation Computer Systems, some work in this area is very recent and was published in many foreign countries During our literature search to compile this survey, we systematically went through over sixty different journals published in various countries and proceedings from over fifty conferences in the last twenty years and over seventy books

Survey on special purpose computer architectures for AI

SUMMARY We have developed the LISTEN (LIMITED SPOKEN TEXT ENcODER) system which automatically recognizes spoken words in isolation for a limited vocabulary. This system is a subpart of the LITHAN (LlsTEN-THINK-ANsWER) speech understanding system 1 ,2). This makes a great feature of the recognition in real time on a mini-computer. Owing to this development, it became capable of trying the various experiments on many speech data. There are other two features in this system: One is to learn the speaker differences by preliminary uttered vowels. The other is that the system is composed of two stages, i.e., phoneme recognition and word recognition. In the latter stage, the effect of coarticulation is taken into account. The system performance obtained the recognition rate of 98.0% on experiments of spoken digits that were uttered by 40 male adults. And also the system obtained the rate of 98.4% on preliminary learning by some spoken digits. When no learning procedure, however, the rate decreased to 95.8%.

/pdf/on-line-real-time-spoken-words-recognition-system-with-lx9dpp7s3v.pdf

On-Line, Real-Time Spoken Words Recognition System with Learning Capability of Speaker Differences.

/pdf/differences-in-feature-parameters-of-japanese-vowels-with-4vhv93ewh4.pdf

Differences in Feature Parameters of Japanese Vowels with Sex and Age

We describe a new tree search method which searches best few paths with backtracking in parallel by the following algorithm(α-β-γ search). Expand the best nodes at one time. If the number of new nodes which have been expanded by a selected node exceeds a preset threshold(β), only the best β nodes are kept and others are pruned. If the total number of newly generated node sequences and non-expanded node sequences exceeds a preset threshold (γ), only the best y node sequences are kept, and others are removed. Repeat these consecutive processes until a complete sequence is generated. We evaluated this method by simulations and experiments, and obtained good performances both in the search efficiency and in the recognition rate.

A parallel tree search method

SUMMARY We have developed LITHAN (LIsten-THink-ANswer) speech understanding system which automatically recognizes continuously uttered speech utilizing higher linguistic information such as syntactic, semantic, pragmatic information. This system predicts possible words utilizing linguistic information at the unrecognized portion of the input utterances, and identifies the predicted word by using the optimum matching algorithm between a recognized phoneme string and the phoneme string of the word dictionary. The system could parse sentences by tree searching, but the results of phoneme recognition and word identification are not always correct, therefore, we propose a new tree search method. LITHAN uses many types of a priori information; the statistic of each pho-neme; the similarity matrix between phonemes; the word dictionary; the spoken grammar with the additional information as regards the spoken grammar; the semantic and pragmatic information. We have applied this efficient, flexible system to restricted utterances which include about 100 words used to perform operational command and query the status of a computer network. When tested on a sample of 200 sentences spoken by 10 male speakers at a normal speed, 64% of the sentences and 93% of the output words were recognized correctly.

/pdf/continuous-speech-understanding-system-lithan-5awqlg8yrc.pdf

Continuous Speech Understanding System LITHAN.

/pdf/some-properties-of-japanese-sounds-through-perceptual-4nqzae4kbd.pdf

Seiichi Nakagawa

Papers

On-Line, Real-Time Spoken Words Recognition System with Learning Capability of Speaker Differences.

Differences in Feature Parameters of Japanese Vowels with Sex and Age

A parallel tree search method

Continuous Speech Understanding System LITHAN.

Some Properties of Japanese Sounds through Perceptual Experiments and Spectral Analysis.