Speaker diarization using data-driven audio sequencing

Houssemeddine Khemiri; Dijana Petrovska-Delacretaz; Gerard Chollet

doi:10.1109/ICASSP.2013.6639169

Speaker diarization using data-driven audio sequencing

Houssemeddine Khemiri, Dijana Petrovska-Delacretaz, Gerard Chollet

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

Abstract

In this paper, a speaker diarization system based on data-driven segmentation is proposed. In addition to the usual segmentation and clustering steps, a new module which detects repeated segments between the same shows broadcasted on different dates is added. This process is achieved by using the ALISP-based audio identification system which segments audio data into pseudo-phonetic units. The ALISP segmentation is then used to identify the similar audio segments in TV and radio shows. The system was evaluated during the ETAPE 2011 evaluation campaign and obtained a Diarization Error Rate - DER of 16.23% which was the best result among seven participants.

Original language	English
Title of host publication	2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages	7736-7740
Number of pages	5
DOIs	https://doi.org/10.1109/ICASSP.2013.6639169
Publication status	Published - 18 Oct 2013
Externally published	Yes
Event	2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada Duration: 26 May 2013 → 31 May 2013

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Country/Territory	Canada
City	Vancouver, BC
Period	26/05/13 → 31/05/13

Keywords

ALISP units
data-driven audio sequencing
speaker diarization

Access to Document

10.1109/ICASSP.2013.6639169

Cite this

Khemiri, H., Petrovska-Delacretaz, D., & Chollet, G. (2013). Speaker diarization using data-driven audio sequencing. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings (pp. 7736-7740). Article 6639169 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2013.6639169

@inproceedings{2b5698f8d702405697ca0372e58d7fb0,

title = "Speaker diarization using data-driven audio sequencing",

abstract = "In this paper, a speaker diarization system based on data-driven segmentation is proposed. In addition to the usual segmentation and clustering steps, a new module which detects repeated segments between the same shows broadcasted on different dates is added. This process is achieved by using the ALISP-based audio identification system which segments audio data into pseudo-phonetic units. The ALISP segmentation is then used to identify the similar audio segments in TV and radio shows. The system was evaluated during the ETAPE 2011 evaluation campaign and obtained a Diarization Error Rate - DER of 16.23\% which was the best result among seven participants.",

keywords = "ALISP units, data-driven audio sequencing, speaker diarization",

author = "Houssemeddine Khemiri and Dijana Petrovska-Delacretaz and Gerard Chollet",

year = "2013",

month = oct,

day = "18",

doi = "10.1109/ICASSP.2013.6639169",

language = "English",

isbn = "9781479903566",

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

pages = "7736--7740",

booktitle = "2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings",

note = "2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 ; Conference date: 26-05-2013 Through 31-05-2013",

}

Khemiri, H, Petrovska-Delacretaz, D & Chollet, G 2013, Speaker diarization using data-driven audio sequencing. in 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings., 6639169, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 7736-7740, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 26/05/13. https://doi.org/10.1109/ICASSP.2013.6639169

Speaker diarization using data-driven audio sequencing. / Khemiri, Houssemeddine; Petrovska-Delacretaz, Dijana; Chollet, Gerard.
2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 7736-7740 6639169 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

TY - GEN

T1 - Speaker diarization using data-driven audio sequencing

AU - Khemiri, Houssemeddine

AU - Petrovska-Delacretaz, Dijana

AU - Chollet, Gerard

PY - 2013/10/18

Y1 - 2013/10/18

N2 - In this paper, a speaker diarization system based on data-driven segmentation is proposed. In addition to the usual segmentation and clustering steps, a new module which detects repeated segments between the same shows broadcasted on different dates is added. This process is achieved by using the ALISP-based audio identification system which segments audio data into pseudo-phonetic units. The ALISP segmentation is then used to identify the similar audio segments in TV and radio shows. The system was evaluated during the ETAPE 2011 evaluation campaign and obtained a Diarization Error Rate - DER of 16.23% which was the best result among seven participants.

AB - In this paper, a speaker diarization system based on data-driven segmentation is proposed. In addition to the usual segmentation and clustering steps, a new module which detects repeated segments between the same shows broadcasted on different dates is added. This process is achieved by using the ALISP-based audio identification system which segments audio data into pseudo-phonetic units. The ALISP segmentation is then used to identify the similar audio segments in TV and radio shows. The system was evaluated during the ETAPE 2011 evaluation campaign and obtained a Diarization Error Rate - DER of 16.23% which was the best result among seven participants.

KW - ALISP units

KW - data-driven audio sequencing

KW - speaker diarization

U2 - 10.1109/ICASSP.2013.6639169

DO - 10.1109/ICASSP.2013.6639169

M3 - Conference contribution

AN - SCOPUS:84890451876

SN - 9781479903566

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 7736

EP - 7740

BT - 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings

T2 - 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013

Y2 - 26 May 2013 through 31 May 2013

ER -

Khemiri H, Petrovska-Delacretaz D, Chollet G. Speaker diarization using data-driven audio sequencing. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 7736-7740. 6639169. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2013.6639169

Speaker diarization using data-driven audio sequencing

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this