Speaker diarization based on locally linear embedding

Ori Shahar; Lee Twito; Nurit Spingarn; Israel Cohen

doi:10.1109/ICSEE.2016.7806168

Speaker diarization based on locally linear embedding

Ori Shahar, Lee Twito, Nurit Spingarn, Israel Cohen

Electrical and Computer Engineering

Technion - Israel Institute of Technology

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

Abstract

Speaker diarization is a significant part of many applications in today's fast growing user-end software and technologies. In the last decade, speaker diarization has attracted significant research effort, however most of the speaker diarization methods deeply rely on statistical models which become unreliable in case of short utterances diarization and in noisy conditions. In this paper, we introduce a speaker diarization system which is based on the Locally Linear Embedding (LLE). The LLE enables to extract the inherent structure of the data and thus provide better clustering. Experimental results show error rates lower than 10% and improved stability in comparison with a conventional speaker diarization method.

Original language	English
Title of host publication	2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016
ISBN (Electronic)	9781509021529
DOIs	https://doi.org/10.1109/ICSEE.2016.7806168
State	Published - 4 Jan 2017
Event	2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016 - Eilat, Israel Duration: 16 Nov 2016 → 18 Nov 2016

Publication series

Name	2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016

Conference

Conference	2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016
Country/Territory	Israel
City	Eilat
Period	16/11/16 → 18/11/16

Keywords

LLE
Speaker diarization
noisy environment
speaker clustering

All Science Journal Classification (ASJC) codes

Computer Science Applications
Hardware and Architecture
Artificial Intelligence
Computer Networks and Communications
Electrical and Electronic Engineering

Access to Document

10.1109/ICSEE.2016.7806168

Cite this

@inproceedings{44a64ae5f0d748358c9c4c0d566fdbd7,

title = "Speaker diarization based on locally linear embedding",

abstract = "Speaker diarization is a significant part of many applications in today's fast growing user-end software and technologies. In the last decade, speaker diarization has attracted significant research effort, however most of the speaker diarization methods deeply rely on statistical models which become unreliable in case of short utterances diarization and in noisy conditions. In this paper, we introduce a speaker diarization system which is based on the Locally Linear Embedding (LLE). The LLE enables to extract the inherent structure of the data and thus provide better clustering. Experimental results show error rates lower than 10\% and improved stability in comparison with a conventional speaker diarization method.",

keywords = "LLE, Speaker diarization, noisy environment, speaker clustering",

author = "Ori Shahar and Lee Twito and Nurit Spingarn and Israel Cohen",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016 ; Conference date: 16-11-2016 Through 18-11-2016",

year = "2017",

month = jan,

day = "4",

doi = "10.1109/ICSEE.2016.7806168",

language = "الإنجليزيّة",

series = "2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016",

booktitle = "2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016",

}

Shahar, O, Twito, L, Spingarn, N & Cohen, I 2017, Speaker diarization based on locally linear embedding. in 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016., 7806168, 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016, 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016, Eilat, Israel, 16/11/16. https://doi.org/10.1109/ICSEE.2016.7806168

Speaker diarization based on locally linear embedding. / Shahar, Ori; Twito, Lee; Spingarn, Nurit et al.
2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016. 2017. 7806168 (2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016).

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

TY - GEN

T1 - Speaker diarization based on locally linear embedding

AU - Shahar, Ori

AU - Twito, Lee

AU - Spingarn, Nurit

AU - Cohen, Israel

PY - 2017/1/4

Y1 - 2017/1/4

N2 - Speaker diarization is a significant part of many applications in today's fast growing user-end software and technologies. In the last decade, speaker diarization has attracted significant research effort, however most of the speaker diarization methods deeply rely on statistical models which become unreliable in case of short utterances diarization and in noisy conditions. In this paper, we introduce a speaker diarization system which is based on the Locally Linear Embedding (LLE). The LLE enables to extract the inherent structure of the data and thus provide better clustering. Experimental results show error rates lower than 10% and improved stability in comparison with a conventional speaker diarization method.

AB - Speaker diarization is a significant part of many applications in today's fast growing user-end software and technologies. In the last decade, speaker diarization has attracted significant research effort, however most of the speaker diarization methods deeply rely on statistical models which become unreliable in case of short utterances diarization and in noisy conditions. In this paper, we introduce a speaker diarization system which is based on the Locally Linear Embedding (LLE). The LLE enables to extract the inherent structure of the data and thus provide better clustering. Experimental results show error rates lower than 10% and improved stability in comparison with a conventional speaker diarization method.

KW - LLE

KW - Speaker diarization

KW - noisy environment

KW - speaker clustering

UR - http://www.scopus.com/inward/record.url?scp=85014191857&partnerID=8YFLogxK

U2 - 10.1109/ICSEE.2016.7806168

DO - 10.1109/ICSEE.2016.7806168

M3 - منشور من مؤتمر

T3 - 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016

BT - 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016

T2 - 2016 IEEE International Conference on the Science of Electrical Engineering, ICSEE 2016

Y2 - 16 November 2016 through 18 November 2016

ER -

Speaker diarization based on locally linear embedding

Abstract

Publication series

Conference

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this