Discrete word recognition using energy-time profiles
- 1 December 1987
- journal article
- Published by Taylor & Francis in International Journal of Electronics
- Vol. 63 (6) , 857-865
- https://doi.org/10.1080/00207218708939191
Abstract
A novel isolated-word recognition system for monosyllabic tonal languages is proposed which depends on the energy-time profiles (ETP) of the utterances at different frequency bands. Training procedures, together with the classification strategy will be discussed. A mean accuracy of 97-99% was achieved for speaker-dependent recognition over the ten Cantonese digits.Keywords
This publication has 7 references indexed in Scilit:
- A modified K-means clustering algorithm for use in isolated work recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985
- A speaker-independent discrete utterance recognition system, combining deterministic and probabilistic strategiesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word RecognitionBell System Technical Journal, 1983
- An improved endpoint detector for isolated word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Dynamic programming algorithm optimization for spoken word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978
- Speech recognition experiments with linear predication, bandpass filtering, and dynamic programmingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- An Algorithm for Determining the Endpoints of Isolated UtterancesBell System Technical Journal, 1975