Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
61.603 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Programes de doctorat
  • Doctorat en Teoria del Senyal i Comunicacions
  • Ponències/Comunicacions de congressos
  • View Item
  •   DSpace Home
  • E-prints
  • Programes de doctorat
  • Doctorat en Teoria del Senyal i Comunicacions
  • Ponències/Comunicacions de congressos
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Auto-encoding nearest neighbor i-vectors for speaker verification

Thumbnail
View/Open
1444.pdf (431,8Kb)
 
10.21437/Interspeech.2019-1444
 
  View Usage Statistics
  LA Referencia / Recolecta stats
Cita com:
hdl:2117/178617

Show full item record
Khan, Umair
India Massana, Miquel ÀngelMés informacióMés informació
Hernando Pericás, Francisco JavierMés informacióMés informacióMés informació
Document typeConference lecture
Defense date2019
PublisherInternational Speech Communication Association (ISCA)
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
ProjectTECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO DE VOZ Y AUDIO (MINECO-TEC2015-69266-P)
Abstract
In the last years, i-vectors followed by cosine or PLDA scoringtechniques were the state-of-the-art approach in speaker veri-fication. PLDA requires labeled background data, and thereexists a significant performance gap between the two scoringtechniques. In this work, we propose to reduce this gap by us-ing an autoencoder to transform i-vector into a new speaker vec-tor representation, which will be referred to as ae-vector. Theautoencoder will be trained to reconstruct neighbor i-vectors in-stead of the same training i-vectors, as usual. These neighbori-vectors will be selected in an unsupervised manner accordingto the highest cosine scores to the training i-vectors. The evalua-tion is performed on the speaker verification trials of VoxCeleb-1 database. The experiments show that our proposed ae-vectorsgain a relative improvement of 42% in terms of EER comparedto the conventional i-vectors using cosine scoring, which fillsthe performance gap between cosine and PLDA scoring tech-niques by 92%, but without using speaker labels
CitationKhan, U.; India, M.; Hernando, J. Auto-encoding nearest neighbor i-vectors for speaker verification. A: Annual Conference of the International Speech Communication Association. "Interspeech 2019: the 20th Annual Conference of the International Speech Communication Association: 15-19 September 2019: Graz, Austria". Baixas: International Speech Communication Association (ISCA), 2019, p. 4060-4064. 
URIhttp://hdl.handle.net/2117/178617
DOI10.21437/Interspeech.2019-1444
ISBN1990-9772
Publisher versionhttps://www.isca-speech.org/archive/Interspeech_2019/pdfs/1444.pdf
Collections
  • Doctorat en Teoria del Senyal i Comunicacions - Ponències/Comunicacions de congressos [214]
  • VEU - Grup de Tractament de la Parla - Ponències/Comunicacions de congressos [437]
  • Departament de Teoria del Senyal i Comunicacions - Ponències/Comunicacions de congressos [3.269]
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
1444.pdf431,8KbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina