Technical improvements of the E-HMM based speaker diarization system for meeting records

Authors:
Corinne Fredouille;Grégory Senay
Affiliations:
LIA, University of Avignon, France;LIA, University of Avignon, France
Venue:
MLMI'06 Proceedings of the Third international conference on Machine Learning for Multimodal Interaction
Year:
2006

Citing 3
Cited 5

Evolutive HMM for multi-speaker tracking system

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Robust speaker segmentation for meetings: the ICSI-SRI spring 2005 diarization system

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
NIST RT'05S evaluation: pre-processing techniques and speaker diarization on multiple microphone meetings

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction

Progress in the AMIDA Speaker Diarization System for Meeting Data

Multimodal Technologies for Perception of Humans
The IBM RT07 Evaluation Systems for Speaker Diarization on Lecture Meetings

Multimodal Technologies for Perception of Humans
The LIA RT'07 Speaker Diarization System

Multimodal Technologies for Perception of Humans
Identification of Soundbite and Its Speaker Name Using Transcripts of Broadcast News Speech

ACM Transactions on Asian Language Information Processing (TALIP)
A review on speaker diarization systems and approaches

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is concerned with the speaker diarization task in the specific context of the meeting room recordings. Firstly, different technical improvements of an E-HMM based system are proposed and evaluated in the framework of the NIST RT'06S evaluation campaign. Related experiments show an absolute gain of 6.4% overall speaker diarization error rate (DER) and 12.9% on the development and evaluation corpora respectively. Secondly, this paper presents an original strategy to deal with the overlapping speech. Indeed, speech overlaps between speakers are largely involved in meetings due to the spontaneous nature of this kind of data and they are responsible for a decrease in performance of the speaker diarization system, if they are not dealt with. Experiments still conducted in the framework of the NIST RT'06S evaluation show the ability of the strategy in detecting overlapping speech (decrease of the missed speaker error rate), even if an overall gain in speaker diarization performance has not been achieved yet.