A large-vocabulary real-time continuous-speech recognition system
- 13 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 789-792 vol.2
- https://doi.org/10.1109/icassp.1989.266546
Abstract
A system architecture has been developed to implement real-time large-vocabulary continuous-speech recognition using HMM (hidden Markov model) algorithms and bigram language models. It is shown that the largest bottleneck in such a system is located in the memory access. The architecture exploits a variety of techniques, such as partitioning and replication, to cope with this memory bottleneck. The required throughput is achieved with the aid of extensive pipelining (up to thirteen levels deep) and concurrency. The architecture allows extension to larger vocabularies by the addition of more parallel units. Pin count considerations have resulted in the definition of five custom integrated circuits which are currently being tested. Using the proposed approach, the authors are currently designing and debugging a real-time 3000-word continuous-speech recognition system that uses bigram language models.<>Keywords
This publication has 6 references indexed in Scilit:
- A speaker-stress resistant HMM isolated word recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- BYBLOS: The BBN continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Linguistic constraints in hidden Markov model based speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Large-vocabulary speaker-independent continuous speech recognition using HMMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An introduction to hidden Markov modelsIEEE ASSP Magazine, 1986
- The development of an experimental discrete dictation recognizerProceedings of the IEEE, 1985