Skip to Main content Skip to Navigation
Conference papers

On robustness of unsupervised domain adaptation for speaker recognition

Abstract : Current speaker recognition systems, that are learned by using wide training datasets and include sophisticated modelings, turn out to be very specific, providing sometimes disappointing results in real-life applications. Any shift between training and test data, in terms of device, language, duration, noise or other tends to degrade accuracy of speaker detection. This study investigates unsupervised domain adaptation,when only a scarce and unlabeled "in-domain" development dataset is available. Details and relevance of different approaches are described and commented, leading to a new robust method that we call feature-Distribution Adaptor. Efficiency of the proposed technique is experimentally validated on the recent NIST 2016 and 2018 Speaker Recognition Evaluation datasets.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02960015
Contributor : Pierre-Michel Bousquet <>
Submitted on : Friday, October 9, 2020 - 10:46:48 AM
Last modification on : Wednesday, October 14, 2020 - 4:22:30 AM
Long-term archiving on: : Sunday, January 10, 2021 - 6:02:40 PM

File

LIA_interSp2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02960015, version 1

Collections

Citation

Pierre-Michel Bousquet, Mickael Rouvier. On robustness of unsupervised domain adaptation for speaker recognition. InterSpeech, Graz University of Technology, Sep 2019, Graz, Austria. ⟨hal-02960015⟩

Share

Metrics

Record views

83

Files downloads

153