Abstract
The present paper dealt with speaker clustering for speech corrupted by noise. In general, the performance of speaker clustering significantly depends on how well the similarities between speech utterances can be measured. The recently proposed i-vector-based cosine similarity has yielded the state-of-the-art performance in speaker clustering systems. However, this similarity often fails to capture the speaker similarity under noisy conditions. Therefore, we attempted to examine the efficiency of spectral clustering on i-vector-based similarity for speech corrupted by noise because spectral clustering can yield robustness against noise by non-linear projection. Experimental comparisons demonstrated that spectral clustering yielded significant improvement from conventional methods, such as agglomerative clustering and k-means clustering, under non-stationary noise conditions.
Original language | English |
---|---|
Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 2041-2045 |
Number of pages | 5 |
Volume | 2015-August |
ISBN (Print) | 9781467369978 |
DOIs | |
Publication status | Published - 2015 Aug 4 |
Event | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 2014 Apr 19 → 2014 Apr 24 |
Other
Other | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 |
---|---|
Country | Australia |
City | Brisbane |
Period | 14/4/19 → 14/4/24 |
Keywords
- i-vector
- noise-robust speaker clustering
- spectral clustering
ASJC Scopus subject areas
- Signal Processing
- Software
- Electrical and Electronic Engineering
Cite this
A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions. / Tawara, Naohiro; Ogawa, Tetsuji; Kobayashi, Tetsunori.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2015-August Institute of Electrical and Electronics Engineers Inc., 2015. p. 2041-2045 7178329.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions
AU - Tawara, Naohiro
AU - Ogawa, Tetsuji
AU - Kobayashi, Tetsunori
PY - 2015/8/4
Y1 - 2015/8/4
N2 - The present paper dealt with speaker clustering for speech corrupted by noise. In general, the performance of speaker clustering significantly depends on how well the similarities between speech utterances can be measured. The recently proposed i-vector-based cosine similarity has yielded the state-of-the-art performance in speaker clustering systems. However, this similarity often fails to capture the speaker similarity under noisy conditions. Therefore, we attempted to examine the efficiency of spectral clustering on i-vector-based similarity for speech corrupted by noise because spectral clustering can yield robustness against noise by non-linear projection. Experimental comparisons demonstrated that spectral clustering yielded significant improvement from conventional methods, such as agglomerative clustering and k-means clustering, under non-stationary noise conditions.
AB - The present paper dealt with speaker clustering for speech corrupted by noise. In general, the performance of speaker clustering significantly depends on how well the similarities between speech utterances can be measured. The recently proposed i-vector-based cosine similarity has yielded the state-of-the-art performance in speaker clustering systems. However, this similarity often fails to capture the speaker similarity under noisy conditions. Therefore, we attempted to examine the efficiency of spectral clustering on i-vector-based similarity for speech corrupted by noise because spectral clustering can yield robustness against noise by non-linear projection. Experimental comparisons demonstrated that spectral clustering yielded significant improvement from conventional methods, such as agglomerative clustering and k-means clustering, under non-stationary noise conditions.
KW - i-vector
KW - noise-robust speaker clustering
KW - spectral clustering
UR - http://www.scopus.com/inward/record.url?scp=84946028651&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84946028651&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2015.7178329
DO - 10.1109/ICASSP.2015.7178329
M3 - Conference contribution
AN - SCOPUS:84946028651
SN - 9781467369978
VL - 2015-August
SP - 2041
EP - 2045
BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
ER -