Abstract
Since wavelet decomposition of signal provides more flexible time-frequency resolutions, it can be utilized as a feature set for speech recognition. In this paper, we explore the possibility to use wavelet decomposition for speech recognition. In particular, we investigate a modified octave structured 5-level filter bank and the HMM (Hidden Markov Model) is used as a recognizer. We present an analysis of various wavelet filters for speech recognition and compare the results with the conventional features that include LPC and mel-cepstrums.
| Original language | English |
|---|---|
| Pages (from-to) | 2891-2894 |
| Number of pages | 4 |
| Journal | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |
| Volume | 4 |
| Publication status | Published - 2000 |
| Event | 2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA Duration: 2000 Oct 8 → 2000 Oct 11 |
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Hardware and Architecture