ICA-Based Speech Features in the Frequency Domain
We apply the technique of independent component analysis to Fourier power coefficients of speech signal frames for a blind detection of basic vectors (sources). A subset of sources corresponding to the noisy influence of basic frequency is identified and its corresponding features could be eliminate...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Buchkapitel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We apply the technique of independent component analysis to Fourier power coefficients of speech signal frames for a blind detection of basic vectors (sources). A subset of sources corresponding to the noisy influence of basic frequency is identified and its corresponding features could be eliminated. The mixing coefficients for such sources are then determined for every speech sample. We compare our features with the Mel Frequency Cepstrum Coefficient (MFCC) features, widely used today for phoneme-based speech recognition. |
---|---|
ISSN: | 0302-9743 1611-3349 |
DOI: | 10.1007/11679363_76 |