The 2016 speakers in thewild speaker recognition evaluation

The newly collected Speakers in the Wild (SITW) database was central to a text-independent speaker recognition challenge held as part of a special session at Interspeech 2016. The SITW database is composed of audio recordings from 299 speakers collected from open source media, with an average of 8 s...

Descripción completa

Guardado en:
Detalles Bibliográficos
Publicado: 2016
Materias:
Evaluation
Speaker recognition
Speakers in the wild database
Audio recordings
Character recognition
Database systems
Speech communication
Speech processing
Acoustic conditions
Evaluation results
Future research directions
International team
Speaker recognition evaluations
Text independents
Speech recognition
Acceso en línea:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_2308457X_v08-12-September-2016_n_p823_McLaren
http://hdl.handle.net/20.500.12110/paper_2308457X_v08-12-September-2016_n_p823_McLaren
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id paper:paper_2308457X_v08-12-September-2016_n_p823_McLaren
record_format dspace
spelling paper:paper_2308457X_v08-12-September-2016_n_p823_McLaren2023-06-08T16:35:31Z The 2016 speakers in thewild speaker recognition evaluation Evaluation Speaker recognition Speakers in the wild database Audio recordings Character recognition Database systems Speech communication Speech processing Acoustic conditions Evaluation Evaluation results Future research directions International team Speaker recognition Speaker recognition evaluations Text independents Speech recognition The newly collected Speakers in the Wild (SITW) database was central to a text-independent speaker recognition challenge held as part of a special session at Interspeech 2016. The SITW database is composed of audio recordings from 299 speakers collected from open source media, with an average of 8 sessions per speaker. The recordings contain unconstrained or "wild" acoustic conditions, rarely found in large speaker recognition datasets, and multi-speaker recordings for both speaker enrollment and verification. This article provides details of the SITW speaker recognition challenge and analysis of evaluation results. There were 25 international teams involved in the challenge of which 11 teams participated in an evaluation track. Teams were tasked with applying existing and novel speaker recognition algorithms to the challenges associated with the real world conditions of SITW. We provide an analysis of some of the top performing systems submitted during the evaluation and provide future research directions. Copyright ©2016 ISCA. 2016 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_2308457X_v08-12-September-2016_n_p823_McLaren http://hdl.handle.net/20.500.12110/paper_2308457X_v08-12-September-2016_n_p823_McLaren
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Evaluation
Speaker recognition
Speakers in the wild database
Audio recordings
Character recognition
Database systems
Speech communication
Speech processing
Acoustic conditions
Evaluation
Evaluation results
Future research directions
International team
Speaker recognition
Speaker recognition evaluations
Text independents
Speech recognition
spellingShingle Evaluation
Speaker recognition
Speakers in the wild database
Audio recordings
Character recognition
Database systems
Speech communication
Speech processing
Acoustic conditions
Evaluation
Evaluation results
Future research directions
International team
Speaker recognition
Speaker recognition evaluations
Text independents
Speech recognition
The 2016 speakers in thewild speaker recognition evaluation
topic_facet Evaluation
Speaker recognition
Speakers in the wild database
Audio recordings
Character recognition
Database systems
Speech communication
Speech processing
Acoustic conditions
Evaluation
Evaluation results
Future research directions
International team
Speaker recognition
Speaker recognition evaluations
Text independents
Speech recognition
description The newly collected Speakers in the Wild (SITW) database was central to a text-independent speaker recognition challenge held as part of a special session at Interspeech 2016. The SITW database is composed of audio recordings from 299 speakers collected from open source media, with an average of 8 sessions per speaker. The recordings contain unconstrained or "wild" acoustic conditions, rarely found in large speaker recognition datasets, and multi-speaker recordings for both speaker enrollment and verification. This article provides details of the SITW speaker recognition challenge and analysis of evaluation results. There were 25 international teams involved in the challenge of which 11 teams participated in an evaluation track. Teams were tasked with applying existing and novel speaker recognition algorithms to the challenges associated with the real world conditions of SITW. We provide an analysis of some of the top performing systems submitted during the evaluation and provide future research directions. Copyright ©2016 ISCA.
title The 2016 speakers in thewild speaker recognition evaluation
title_short The 2016 speakers in thewild speaker recognition evaluation
title_full The 2016 speakers in thewild speaker recognition evaluation
title_fullStr The 2016 speakers in thewild speaker recognition evaluation
title_full_unstemmed The 2016 speakers in thewild speaker recognition evaluation
title_sort 2016 speakers in thewild speaker recognition evaluation
publishDate 2016
url https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_2308457X_v08-12-September-2016_n_p823_McLaren
http://hdl.handle.net/20.500.12110/paper_2308457X_v08-12-September-2016_n_p823_McLaren
_version_ 1768542056792195072

Ejemplares similares