Paper Info
Title
Lattice Mllr Based M-Vector System For Speaker Verification
Abstract
The recently introduced m-vector approach uses Maximum Likelihood Linear Regression (MLLR) super-vectors for speaker verification, where MLLR super-vectors are estimated with respect to a Universal Background Model (UBM) without any transcription of speech segments and speaker m-vectors are obtained by uniform segmentation of their MLLR super-vectors. Hence, this approach does not exploit the phonetic content of the speech segments. In this paper, we propose the integration of an Automatic Speech Recognition (ASR) based multi-class MLLR transformation into the m-vector system. We consider two variants, with MLLR transformations computed either on the 1-best (hypothesis) or on the lattice word transcriptions. The former case is able to account for the risk of ASR transcription errors. We show that the proposed systems outperform the conventional method over various tasks of the NIST SRE 2008 core condition.
Year
DOI
Venue
2013
10.1109/ICASSP.2013.6639152
2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
m-Vector, Lattice MLLR, MLLR Super-Vector, Session Variability Compensation, Speaker Verification
Speaker verification,Transcription (linguistics),Lattice (order),Pattern recognition,Segmentation,Computer science,Regression analysis,Speech recognition,Maximum likelihood linear regression,Speaker recognition,NIST,Artificial intelligence
Conference
ISSN
Citations 
PageRank 
1520-6149
1
0.39
References 
Authors
12
3
Name
Order
Citations
PageRank
Achintya Kumar Sarkar1237.81
Claude Barras244970.53
Viet Bac Le314012.62