Continuous speech recognition by statistical methods
F. Jelinek · Proceedings of the IEEE · 1976
Statistical methods useful in automatic recognition of continuous speech are described. They concern modeling of a speaker and of an acoustic processor, extraction of the models' statistical parameters and hypothesis search procedures and likelihood computations of linguistic decoding. Experimental results are presented that indicate the power of the methods.
Cited by 920 works. doi:10.1109/proc.1976.10159
Authors
References
- Information Theory and Reliable Communication
- Information Theory and Reliable Communication.
- Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
- The viterbi algorithm
- Optimal decoding of linear codes for minimizing symbol error rate (Corresp.)
- Optimal decoding of linear codes for minimizing symbol error rate
- A Formal Basis for the Heuristic Determination of Minimum Cost Paths
- A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
- Statistical Inference for Probabilistic Functions of Finite State Markov Chains
- Information Theory and Coding.