Isolated-word speech recognition using multisection vector quantization codebooks
D. Burton, John E. Shore, J. Buck · IEEE Transactions on Acoustics Speech and Signal Processing · 1985
A new approach to isolated-word speech recognition using vector quantization (VQ) is examined. In this approach, words are recognized by means of sequences of VQ codebooks, called multisection codebooks. A separate multisection codebook is designed for each word in the recognition vocabulary by dividing the word into equal-length sections and designing a standard VQ codebook for each section. Unknown words are classified by dividing them into corresponding sections, encoding them with the multisection codebooks, and finding the multisection codebook that yields the smallest average distortion. For speaker-independent recognition of the digits, this approach achieved a recognition accuracy of 98 percent. In addition, the approach achieved greater than 99 percent accuracy for speaker-dependent recognition of the digits with only one distortion computation per input frame per vocabulary word. The approach is described, detailed experimental results are presented and discussed, and computational requirements are analyzed.
Cited by 56 works. doi:10.1109/tassp.1985.1164650
Authors
References
- An Algorithm for Vector Quantizer Design
- Minimum prediction residual principle applied to speech recognition
- Vector Quantization
- Continuous speech recognition by statistical methods
- The DRAGON system--An overview
- Speech coding based upon vector quantization
- A database for speaker-independent digit recognition
- Distortion measures for speech processing
- Rate Distortion Theory: A Mathematical Basis for Data Compression
- On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition