eprintid: 4312
rev_number: 25
eprint_status: archive
userid: 1903
dir: disk0/00/00/43/12
datestamp: 2010-09-27 08:32:01
lastmod: 2016-04-20 13:35:57
status_changed: 2010-09-27 08:32:01
type: conference_item
metadata_visibility: show
item_issues_count: 0
creators_name: Torre Toledano, Doroteo
creators_name: Esteve-Elizalde, Cristina
creators_name: Gonzalez-Rodriguez, Joaquin
creators_name: Fernández Pozo, Rubén
creators_name: Hernández Gómez, Luis Alfonso
title: Phoneme and Sub-Phoneme T-Normalization for Text-Dependent Speaker Recognition
ispublished: pub
subjects: telecomunicaciones
abstract: Test normalization (T-Norm) is a score normalization technique that is regularly and successfully applied in the context of text-independent speaker recognition. It is less frequently applied, however, to text-dependent or textprompted speaker recognition, mainly because its improvement in this context is more modest. In this paper we present a novel way to improve the performance of T-Norm for text-dependent systems. It consists in applying score TNormalization at the phoneme or sub-phoneme level instead of at the sentence level. Experiments on the YOHO corpus show that, while using standard sentence-level T-Norm does not improve equal error rate (EER), phoneme and sub-phoneme level T-Norm produce a relative EER reduction of 18.9% and 20.1% respectively on a state-of-the-art HMM based textdependent speaker recognition system. Results are even better for working points with low false acceptance rates.
date: 2008
date_type: published
publisher: IEEE
official_url: http://www.isca-speech.org/archive/odyssey_2008/od08_029.html
full_text_status: public
pres_type: paper
place_of_pub: EEUU
event_title: IEEE Odyssey 2008 Workshop on Speaker and Language Recognition
event_location: Stellenbosch, Sudáfrica
event_dates: 21/01/2008-24/01/2008
event_type: conference
institution: Telecomunicacion
department: Senales
refereed: TRUE
isbn: 978-0-620-40331-3
book_title: Proceedings of the IEEE Odyssey 2008 Workshop on Speaker and Language Recognition
rights: by-nc-nd
citation:   Torre Toledano, Doroteo and Esteve-Elizalde, Cristina and Gonzalez-Rodriguez, Joaquin and Fernández Pozo, Rubén and Hernández Gómez, Luis Alfonso  (2008).  Phoneme and Sub-Phoneme T-Normalization for Text-Dependent Speaker Recognition.  In: "IEEE Odyssey 2008 Workshop on Speaker and Language Recognition", 21/01/2008-24/01/2008, Stellenbosch, Sudáfrica. ISBN 978-0-620-40331-3.    
document_url: https://oa.upm.es/4312/1/INVE_MEM_2008_59711.pdf