Dynamic programming, the viterbi algorithm, and low cost speech recognition
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 413-417
- https://doi.org/10.1109/icassp.1978.1170385
Abstract
Dynamic Programming, the Viterbi Algorithm, the theory of finite state machines, and the mathematics of Markov processes are well developed formalisms that can be applied to the problem of pattern matching acoustic events in speech. At the intersection of these formalisms are a set of computationally efficient but powerful algorithms that are a significant improvement over the commonly used pattern matching schemes for handling temporal and spacial deviation from idealized prototypes. This paper will describe some of these relatively new pattern matching algorithms. It will be shown that they reduce to simple forms that promote low cost isolated word and continuous speech recognition.Keywords
This publication has 6 references indexed in Scilit:
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976
- Applications of a nonlinear smoothing algorithm to speech processingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
- Minimum prediction residual principle applied to speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
- The viterbi algorithmProceedings of the IEEE, 1973
- Automatic recognition of 200 wordsInternational Journal of Man-Machine Studies, 1970
- Error bounds for convolutional codes and an asymptotically optimum decoding algorithmIEEE Transactions on Information Theory, 1967