Factorised representations for neural network adaptation to diverse acoustic environments

Joachim Fainberg, Steve Renals, Peter Bell

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


Adapting acoustic models jointly to both speaker and environment has been shown to be effective. In many realistic scenarios, however, either the speaker or environment at test time might be unknown, or there may be insufficient data to learn a joint transform. Generating independent speaker and environment transforms improves the match of an acoustic model to unseen combinations. Using i-vectors, we demonstrate that it is possible to factorise speaker or environment information using multi-condition training with neural networks. Specifically, we extract bottleneck features from networks trained to classify either speakers or environments. We perform experiments on the Wall Street Journal corpus combined with environment noise from the Diverse Environments Multichannel Acoustic Noise Database. Using the factorised i-vectors we show improvements in word error rates on perturbed versions of the eval92 and dev93 test sets, both when one factor is missing and when the factors are seen but not in the desired combination.
Original languageEnglish
Title of host publicationProceedings Interspeech 2017
PublisherInternational Speech Communication Association
Number of pages5
Publication statusPublished - 24 Aug 2017
EventInterspeech 2017 - Stockholm, Sweden
Duration: 20 Aug 201724 Aug 2017

Publication series

PublisherInternational Speech Communcaition Association
ISSN (Print)1990-9772


ConferenceInterspeech 2017
Internet address


Dive into the research topics of 'Factorised representations for neural network adaptation to diverse acoustic environments'. Together they form a unique fingerprint.

Cite this