Edinburgh Research Explorer

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

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

Original languageEnglish
Title of host publicationProc. of Interspeech 2018
Place of PublicationHyderabad, India
Number of pages5
Publication statusPublished - Sep 2018
EventInterspeech 2018 - Hyderabad International Convention Centre, Hyderabad, India
Duration: 2 Sep 20186 Sep 2018


ConferenceInterspeech 2018
Internet address


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.


Interspeech 2018


Hyderabad, India

Event: Conference

Download statistics

No data available

ID: 74660218