Paper Info
Title
Further optimisations of constant Q cepstral processing for integrated utterance and text-dependent speaker verification
Abstract
Many authentication applications involving automatic speaker verification (ASV) demand robust performance using short-duration, fixed or prompted text utterances. Text constraints not only reduce the phone-mismatch between enrolment and test utterances, which generally leads to improved performance, but also provide an ancillary level of security. This can take the form of explicit utterance verification (UV). An integrated UV + ASV system should then verify access attempts which contain not just the expected speaker, but also the expected text content. This paper presents such a system and introduces new features which are used for both UV and ASV tasks. Based upon multi-resolution, spectro-temporal analysis and when fused with more traditional parameterisations, the new features not only generally outperform Mel-frequency cepstral coefficients, but also are shown to be complementary when fusing systems at score level. Finally, the joint operation of UV and ASV greatly decreases false acceptances for unmatched text trials.
Year
DOI
Venue
2016
10.1109/SLT.2016.7846262
2016 IEEE Spoken Language Technology Workshop (SLT)
Keywords
Field
DocType
speaker verification,utterance verification,text dependent,constant Q transform
Constant Q transform,Mel-frequency cepstrum,Algorithm design,Authentication,Pattern recognition,Computer science,Cepstrum,Utterance,Speech recognition,Time–frequency analysis,Artificial intelligence,Hidden Markov model
Conference
ISSN
ISBN
Citations 
2639-5479
978-1-5090-4904-2
1
PageRank 
References 
Authors
0.35
0
7
Name
Order
Citations
PageRank
hector delgado17810.47
Massimiliano Todisco213817.80
Md. Sahidullah310.35
Achintya Kumar Sarkar4237.81
nicholas evans559454.41
Tomi Kinnunen6132386.67
Zheng-Hua Tan745760.32