Ir directamente a la navegación principal Ir directamente a la búsqueda Ir directamente al contenido principal

Speech recognition using reconstructed phase space features

Producción científica: Conference article › revisión exhaustiva

40 Citas (Scopus)

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 originalEnglish
Páginas (desde-hasta)60-63
Número de páginas4
PublicaciónICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volumen1
EstadoPublished - 2003
Evento2003 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