Výsledky vyhledávání - "Jesús Antonio Villalba López"

Unsupervised Accent Modeling for Language Identification

Autor: David Martínez González, Eduardo Lleida Solano, Jesús Antonio Villalba López, Alfonso Ortega Giménez

Publikováno v: Advances in Speech and Language Technologies for Iberian Languages ISBN: 9783319136226
IberSPEECH

In this paper we propose to cluster iVectors to model different accents within a language. The motivation is that not all the speakers of the same language have the same pronunciation style. This source of variability is not usually considered in sta

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c70e044e6683ca4e5ae3973582f7fa3f
https://doi.org/10.1007/978-3-319-13623-3_6

Zobrazit plný text záznamu

A new bayesian network to assess the reliability of speaker verification decisions

Autor: Antonio Miguel, Jesús Antonio Villalba López, Eduardo Lleida, Alfonso Ortega

Publikováno v: Scopus-Elsevier
ResearcherID
INTERSPEECH

In some situations the quality of the signals involved in a speaker verification trial is not as good as needed to take a reliable decision. In this work, we present a new method based on Bayesian networks and quality measures to estimate if the tria

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c3215a7597441ec09b4b316660eeabc
http://www.scopus.com/inward/record.url?eid=2-s2.0-84906230291&partnerID=MN8TOARS

Zobrazit plný text záznamu

Handling recordings acquired simultaneously over multiple channels with PLDA

Autor: Eduardo Lleida, Jesús Antonio Villalba López, Mireia Diez, Amparo Varona

Publikováno v: Scopus-Elsevier
INTERSPEECH
ResearcherID

In some speaker recognition scenarios we find conversations recorded simultaneously over multiple channels. That is the case of the interviews in the NIST SRE dataset. To take advantage of that, we propose a modification of the PLDA model that consid

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e98f44d8d207edcb63d9eebe93d7a4eb
http://www.scopus.com/inward/record.url?eid=2-s2.0-84906251903&partnerID=MN8TOARS

Zobrazit plný text záznamu

Spoofing detection with DNN and one-class SVM for the ASVspoof 2015 challenge

Autor: Antonio Miguel, Alfonso Ortega, Jesús Antonio Villalba López, Eduardo Lleida

Publikováno v: Scopus-Elsevier
INTERSPEECH

Speaker verification systems have achieved great performance in recent times. However, we usually measure performance on a ideal scenarios with naive impostors that do not modify their voices to impersonate the target speakers. The fact of impersonat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d4681bdbc4764fa256ce099dc289db4
http://www.scopus.com/inward/record.url?eid=2-s2.0-84959161293&partnerID=MN8TOARS

Zobrazit plný text záznamu

The I3A speaker recognition system for NIST SRE12: Post-evaluation analysis

Autor: Eduardo Lleida, Antonio Miguel, Alfonso Ortega, Jesús Antonio Villalba López

Publikováno v: Scopus-Elsevier
INTERSPEECH
ResearcherID

The I3A submission for the recent NIST 2012 speaker recognition evaluation (SRE) was based on the i-vector approach with a multi-channel PLDA classifier. This PLDA is modified so that, for each i-vector, the between-class covariance depends on the ty

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7bc842bb09d5f425c970fe4864a9a0a
http://www.scopus.com/inward/record.url?eid=2-s2.0-84906236540&partnerID=MN8TOARS

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání