Resumen
This paper presents a novel method for speech recognition by utilizing nonlinear/chaotic signal processing techniques to extract time-domain based phase space features. By exploiting the theoretical results derived in nonlinear dynamics, a processing space called a reconstructed phase space can be generated where a salient model (the natural distribution of the attractor) can be extracted for speech recognition. To discover the discriminatory power of these features, isolated phoneme classification experiments were performed using the TIMIT corpus and compared to a baseline classifier that uses MFCC features. The results demonstrate that phase space features contain substantial discriminatory power, even though MFCC features outperformed the phase space features on direct comparisons. The authors conjecture that phase space and MFCC features used in combination within a classifier will yield increased accuracy for various speech recognition tasks.
| Idioma original | English |
|---|---|
| Páginas (desde-hasta) | 60-63 |
| Número de páginas | 4 |
| Publicación | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Volumen | 1 |
| Estado | Published - 2003 |
| Evento | 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2003 - Hong Kong, Hong Kong Duración: abr 6 2003 → abr 10 2003 |
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering
Huella
Profundice en los temas de investigación de 'Speech recognition using reconstructed phase space features'. En conjunto forman una huella única.Citar esto
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver