Acoustic Model Compression with MAP adaptation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

21 Downloads (Pure)

Abstract

Speaker adaptation is an important step in optimization and personalization of the performance of automatic speech recognition (ASR) for individual users. While many applications target in rapid adaptation by various global transformations, slower adaptation to obtain a higher level of personalization would be useful for many active ASR users, especially for those whose speech is not recognized well. This paper studies the outcome of combinations of maximum a posterior (MAP) adaptation and compression of Gaussian mixture models. An important result that has not received much previous attention is how MAP adaptation can be utilized to radically decrease the size of the models as they get tuned to a particular speaker. This is particularly relevant for small personal devices which should provide accurate recognition in real-time despite a low memory, computation, and electricity consumption. With our method we are able to decrease the model complexity with MAP adaptation while increasing the accuracy.
Original languageEnglish
Title of host publicationProceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017, Gothenburg, Sweden
EditorsJörg Tiedemann
PublisherLINKÖPING UNIVERSITY ELECTRONIC PRESS
Pages65-69
Number of pages5
ISBN (Print)978-91-7685-601-7
Publication statusPublished - 2017
MoE publication typeA4 Article in a conference publication
EventNordic Conference on Computational Linguistics - Gothenburg, Sweden
Duration: 22 May 201724 May 2017
Conference number: 21

Publication series

NameLinköping Electronic Conference Proceedings
PublisherLinköping University Electronic Press
Volume131
ISSN (Print)1659-3686
ISSN (Electronic)1650-3740

Conference

ConferenceNordic Conference on Computational Linguistics
Abbreviated titleNoDaLiDa
CountrySweden
CityGothenburg
Period22/05/201724/05/2017

Keywords

  • MAP adaptation
  • acoustic model adaptation
  • Speech recognition
  • Compression
  • acoustic model compression
  • Speaker adaptation

Fingerprint Dive into the research topics of 'Acoustic Model Compression with MAP adaptation'. Together they form a unique fingerprint.

Cite this