Result Details

Analysis of Score Normalization in Multilingual Speaker Recognition

MATĚJKA, P.; NOVOTNÝ, O.; PLCHOT, O.; BURGET, L.; DIEZ SÁNCHEZ, M.; ČERNOCKÝ, J. Analysis of Score Normalization in Multilingual Speaker Recognition. In Proceedings of Interspeech 2017. Proceedings of Interspeech. Stockholm: International Speech Communication Association, 2017. no. 08, p. 1567-1571. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Matějka Pavel, Ing., Ph.D., DCGM (FIT)
Novotný Ondřej, Ing., Ph.D., DCGM (FIT)
Plchot Oldřich, Ing., Ph.D., DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Diez Sánchez Mireia, M.Sc., Ph.D., DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Abstract

This paper is about the analysis of score normalization in multilingual speaker recognition. Several normalization techniques are compared in this paper as well as different cohorts and analyzes the nature of files selected to the cohort in adaptive score normalization.

Keywords

speaker recognition, score normalization

URL
Annotation

NIST Speaker Recognition Evaluation 2016 has revealed the importance of score normalization for mismatched data conditions. This paper analyzes several score normalization techniques for test conditions with multiple languages. The best performing one for a PLDA classifier is an adaptive s-norm with 30% relative improvement over the system without any score normalization. The analysis shows that the adaptive score normalization (using top scoring files per trial) selects cohorts that in 68% contain recordings from the same language and in 92% of the same gender as the enrollment and test recordings. Our results suggest that the data to select score normalization cohorts should be a pool of several languages and channels and if possible, its subset should contain data from the target domain.

Published
2017
Pages
1567–1571
Journal
Proceedings of Interspeech, vol. 2017, no. 08, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2017
Conference
Interspeech Conference
Publisher
International Speech Communication Association
Place
Stockholm
DOI
10.21437/Interspeech.2017-803
UT WoS
000457505000324
EID Scopus
2-s2.0-85039148235
BibTeX 
@inproceedings{BUT144487,
  author="Pavel {Matějka} and Ondřej {Novotný} and Oldřich {Plchot} and Lukáš {Burget} and Mireia {Diez Sánchez} and Jan {Černocký}",
  title="Analysis of Score Normalization in Multilingual Speaker Recognition",
  booktitle="Proceedings of Interspeech 2017",
  year="2017",
  journal="Proceedings of Interspeech",
  volume="2017",
  number="08",
  pages="1567--1571",
  publisher="International Speech Communication Association",
  address="Stockholm",
  doi="10.21437/Interspeech.2017-803",
  issn="1990-9772",
  url="http://www.isca-speech.org/archive/Interspeech_2017/pdfs/0803.PDF"
}
Files
Projects
Big speech data analytics for contact centers, EU, Horizon 2020, start: 2015-01-01, end: 2017-12-31, completed
DARPA Robust Automatic Transcription of Speech (RATS) - RATS Patrol I, BBN, start: 2010-09-23, end: 2014-06-30, completed
Information mining in speech acquired by distant microphones, MV, Bezpečnostní výzkum České republiky 2015-2020, VI20152020025, start: 2015-10-01, end: 2020-09-30, completed
IT4Innovations excellence in science, MŠMT, Národní program udržitelnosti II, LQ1602, start: 2016-01-01, end: 2020-12-31, completed
Robust SPEAKER DIariazation systems using Bayesian inferenCE and deep learning methods, EU, Horizon 2020, start: 2017-03-01, end: 2019-02-28, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top