A Parallel Speech Recognition Model on Distributed Memory Multiprocessors

분산 메모리 다중프로세서 환경에서의 병렬 음성인식 모델

  • Published : 1999.07.01

Abstract

This paper presents a massively parallel computational model for the efficient integration of speech and natural language understanding. The phoneme model is based on continuous Hidden Markov Model with context dependent phonemes, and the language model is based on a knowledge base approach. To construct the knowledge base, we adopt a hierarchically-structured semantic network and a memory-based parsing technique that employs parallel marker-passing as an inference mechanism. Our parallel speech recognition algorithm is implemented in a multi-Transputer system using distributed-memory MIMD multiprocessors. Experimental results show that the parallel speech recognition system performs better in recognition accuracy than a word network-based speech recognition system. The recognition accuracy is further improved by applying code-phoneme statistics. Besides, speedup experiments demonstrate the possibility of constructing a realtime parallel speech recognition system.

본 논문에서는 음성과 자연언어의 통합처리를 위한 효과적인 병렬계산모델을 제안한다. 음소모델은 연속 Hidden Markov Model(HMM)에 기반을 둔 문맥종속형 음소를 사용하며, 언어모델은 지식베이스를 기반으로 한다. 또한 지식베이스를 구성하기 위해 계층구조의 semantic network과 병렬 marker-passing을 추론 메카니즘으로 쓰는 memory-based parsing 기술을 사용한다. 본 연구의 병렬 음성인식 알고리즘은 분산메모리 MIMD(Multiple Instruction Multiple Data) 구조의 다중 Transputer 시스템을 이용하여 구현되었다. 실험결과, 본 연구의 지식베이스 기반 음성인식 시스템의 인식률이 word network 기반 음성인식 시스템보다 높게 나타났으며 code-phoneme 통계정보를 활용하여 인식성능의 향상도 얻을 수 있었다. 또한, 성능향상도(speedup) 관련 실험들을 통하여 병렬 음성인식 시스템의 실시간 구현 가능성을 확인하였다.

Keywords

References

  1. Survey of Current Speech Technology A. I. Rudnicky;A. G. Hauptmann
  2. IEEE Transactions on Computers v.42 no.10 A Parallel Computational Model for Integrated Speech and Natural Language Understanding S. H. Chung,;D. I. Moldovan,;R. F. DeMara
  3. Proceedings of IJCAI A Parallel Parser for Spoken Natural Language E. P. Giachin;C. Rullent
  4. Proceedings of COLING-86 Parsing Spoken Language: a Semantic Caseframe Approach P. J. Hayes;A. G. Hauptmann;J. G. Carbonell;M. Tomita
  5. M. Sc. thesis, Alparon report, nr.96-03, Delft University of Technology Parallel Implementation of Hidden Markov Models on the nCUBE2 G. Huijsen
  6. Proceedings of COLING-86 Parsing in Parallel X. Huang;L. Guthrie
  7. Machine Translation v.5 ФDM-Dialog: A Speech-to-speech Dialogue Translation System H. Kitano
  8. Advances in Speech Signal Processing Continuous Speech Recognition K. F. Lee;F. Alleva
  9. Final report, ETRI Design and Construction of Korean Speech Database Y. J. Lee
  10. Linear Prediction of Speech J. D. Markel,;A. H. Gary, Jr.
  11. IEEE Trans. ASSP Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences S. Davis;P. Mermelstein
  12. Recent Advances in Speech Understanding and Dialog Systems Modification of Earley's Algorithm for Speech Understanding A. Paeseler
  13. Fundamentals of speech recognition L. R. Rabiner,;Biing-Hwang Juang
  14. Proceedings of EUROSPEECH-95 The AT&T 60,000 word speech-to-text system M. D. Riley;A. Ljolje;D. Hindle;F. Pereira
  15. Preceedings of EUROSPEECH- 97 Parallel Speech Recognition Steven Phillips;Anne Rogers
  16. Cognitive Science v.9 Massively Parallel Parsing :A Strong Interactive Model of Natural Language Interpretation D. L. Waltz;J. B. Pollack
  17. Communication of ACM v.32 no.2 High Level Knowledge Sources in Usable Speech Recognition Systems S. R. Young(et al.)
  18. 용역결과보고서, 한국전자통신연구소 음성 데이터베이스 설계 및 제작 이용주