Learning to Adapt: a Meta-learning Approach for Speaker Adaptation

Ondrej Klejch, Joachim Fainberg, Peter Bell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The performance of automatic speech recognition systems can be improved by adapting an acoustic model to compensate for the mismatch between training and testing conditions, for example by adapting to unseen speakers. The success of speaker adaptation methods relies on selecting weights that are suitable for adaptation and using good adaptation schedules to update these weights in order not to overfit to the adaptation data. In this paper we investigate a principled way of adapting all the weights of the acoustic model using a meta-learning. We show that the meta-learner can learn to perform supervised and unsupervised speaker adaptation and that it outperforms a strong baseline adapting LHUC parameters when adapting a DNN AM with 1.5M parameters. We also report initial experiments on adapting TDNN AMs,
where the meta-learner achieves comparable performance with LHUC.
Original languageEnglish
Title of host publicationProc. of Interspeech 2018
Place of PublicationHyderabad, India
PublisherISCA
Pages867-871
Number of pages5
DOIs
Publication statusPublished - Sept 2018
EventInterspeech 2018 - Hyderabad International Convention Centre, Hyderabad, India
Duration: 2 Sept 20186 Sept 2018
http://interspeech2018.org/

Publication series

Name
PublisherISCA
ISSN (Electronic)1990-9772

Conference

ConferenceInterspeech 2018
Country/TerritoryIndia
CityHyderabad
Period2/09/186/09/18
Internet address

Fingerprint

Dive into the research topics of 'Learning to Adapt: a Meta-learning Approach for Speaker Adaptation'. Together they form a unique fingerprint.

Cite this