A Survey on Automatic Speech Recognition with an Illustrative Example on Continuous Speech Recognition of Mandarin

Chin-Hui Lee ； Biing-Hwang Juang

《中文計算語言學期刊》 1卷1期 (1996/08) Pp. 1-36

https://doi.org/10.30019/IJCLCLP.199608.0001

並列摘要

For the past two decades, research in speech recognition has been intensively carried out worldwide, spurred on by advances in signal processing, algorithms, architectures, and hardware. Speech recognition systems have been developed for a wide variety of applications, ranging from small vocabulary keyword recognition over dial-up telephone lines, to medium size vocabulary voice interactive command and control systems on personal computers, to large vocabulary speech dictation, spontaneous speech understanding, and limited-domain speech translation. In this paper we review some of the key advances in several areas of automatic speech recognition. We also illustrate, by examples, how these key advances can be used for continuous speech recognition of Mandarin. Finally we elaborate the requirements in designing successful real-world applications and address technical challenges that need to be harnessed in order to reach the ultimate goal of providing an easy-to-use, natural, and flexible voice interface between people and machines.

並列關鍵字

hidden Markov modeling ； dynamic programming ； speech recognition ； acoustic modeling ； Mandarin speech recognition ； spoken language systems

參考文獻

Bourlard, H.(1994).Connectionist Speech Recognition-A Hybrid Approach.

Bourlard, H.,Wellekens, C. J.(1992).Links between Markov Models and Multi-Layer Perceptron.IEEE Transactions On Pattern Analysis and Machine Intelligence.12,1167-1178.

Brown, P. F.,De Souza, P. V.,Bahl, L. R.,Mercer, R. L.(1986).Proc. IEEE ICASSP - 86.

Brown, P. F.,De Souza, P. V.,Bahl, L. R.,Mercer, R. L.(1989).Tree-Based Language Model for Natural Language Speech Recognition.IEEE transactions on acoustics, speech, and signal processing .37,1001-1008.

Digalakis, V.,Weintraub, M.,Weintraub, M.,Murveit, H.,Butzberger, J.(1993).Proc. IEEE ICASSP.