Abstract
In this paper, we proposed new speech features using independent component analysis to human speeches. When independent component analysis is applied to speech signals for efficient encoding the adapted basis functions resemble Gabor-like features. Trained basis functions have some redundancies, so we select some of the basis functions by reordering method. The basis functions are almost ordered from low frequency basis vector to high frequency basis vector. And this is compatible with the fact that human speech signals have much more information on low frequency range. Those features can be used in automatic speech recognition systems and the proposed method gives much better recognition rates than conventional mel-frequency cepstral features.
| Original language | English |
|---|---|
| Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Publisher | IEEE |
| Pages | 1631-1634 |
| Number of pages | 4 |
| Volume | 3 |
| Publication status | Published - 2000 |
| Externally published | Yes |
| Event | 2000 IEEE Interntional Conference on Acoustics, Speech, and Signal Processing - Istanbul, Turkey Duration: 2000 Jun 5 → 2000 Jun 9 |
Other
| Other | 2000 IEEE Interntional Conference on Acoustics, Speech, and Signal Processing |
|---|---|
| City | Istanbul, Turkey |
| Period | 00/6/5 → 00/6/9 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Acoustics and Ultrasonics
Cite this
Speech feature extraction using independent component analysis. / Lee, Jong-Hwan; Jung, Ho Young; Lee, Te Won; Lee, Soo Young.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 3 IEEE, 2000. p. 1631-1634.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Speech feature extraction using independent component analysis
AU - Lee, Jong-Hwan
AU - Jung, Ho Young
AU - Lee, Te Won
AU - Lee, Soo Young
PY - 2000
Y1 - 2000
N2 - In this paper, we proposed new speech features using independent component analysis to human speeches. When independent component analysis is applied to speech signals for efficient encoding the adapted basis functions resemble Gabor-like features. Trained basis functions have some redundancies, so we select some of the basis functions by reordering method. The basis functions are almost ordered from low frequency basis vector to high frequency basis vector. And this is compatible with the fact that human speech signals have much more information on low frequency range. Those features can be used in automatic speech recognition systems and the proposed method gives much better recognition rates than conventional mel-frequency cepstral features.
AB - In this paper, we proposed new speech features using independent component analysis to human speeches. When independent component analysis is applied to speech signals for efficient encoding the adapted basis functions resemble Gabor-like features. Trained basis functions have some redundancies, so we select some of the basis functions by reordering method. The basis functions are almost ordered from low frequency basis vector to high frequency basis vector. And this is compatible with the fact that human speech signals have much more information on low frequency range. Those features can be used in automatic speech recognition systems and the proposed method gives much better recognition rates than conventional mel-frequency cepstral features.
UR - http://www.scopus.com/inward/record.url?scp=0033692615&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033692615&partnerID=8YFLogxK
M3 - Conference contribution
VL - 3
SP - 1631
EP - 1634
BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PB - IEEE
ER -