A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions

Naohiro Tawara; Tetsuji Ogawa; Tetsunori Kobayashi

doi:10.1109/ICASSP.2015.7178329

A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions

Naohiro Tawara, Tetsuji Ogawa, Tetsunori Kobayashi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

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	https://doi.org/10.1109/ICASSP.2015.7178329
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/Territory	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

Access to Document

10.1109/ICASSP.2015.7178329

Cite this

Tawara, N., Ogawa, T., & Kobayashi, T. (2015). A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 2015-August, pp. 2041-2045). [7178329] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2015.7178329

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

Tawara, N, Ogawa, T & Kobayashi, T 2015, A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 2015-August, 7178329, Institute of Electrical and Electronics Engineers Inc., pp. 2041-2045, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 14/4/19. https://doi.org/10.1109/ICASSP.2015.7178329

Tawara N, Ogawa T , Kobayashi T. A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions. In 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 https://doi.org/10.1109/ICASSP.2015.7178329

@inproceedings{0220d06cc84b43e98972ef1fa6ebb4da,

title = "A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions",

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.",

keywords = "i-vector, noise-robust speaker clustering, spectral clustering",

author = "Naohiro Tawara and Tetsuji Ogawa and Tetsunori Kobayashi",

year = "2015",

month = aug,

day = "4",

doi = "10.1109/ICASSP.2015.7178329",

language = "English",

isbn = "9781467369978",

volume = "2015-August",

pages = "2041--2045",

booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 ; Conference date: 19-04-2014 Through 24-04-2014",

}

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.

T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

Y2 - 19 April 2014 through 24 April 2014

ER -

A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this