Acoustic Model Compression with MAP adaptation

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

29 Lataukset (Pure)

Abstrakti

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.
AlkuperäiskieliEnglanti
OtsikkoProceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017, Gothenburg, Sweden
ToimittajatJörg Tiedemann
KustantajaLINKÖPING UNIVERSITY ELECTRONIC PRESS
Sivut65-69
Sivumäärä5
ISBN (painettu)978-91-7685-601-7
TilaJulkaistu - 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaNORDIC CONFERENCE ON COMPUTATIONAL LINGUISTICS - Gothenburg, Ruotsi
Kesto: 22 toukok. 201724 toukok. 2017
Konferenssinumero: 21

Julkaisusarja

NimiLinköping Electronic Conference Proceedings
KustantajaLinköping University Electronic Press
Vuosikerta131
ISSN (painettu)1659-3686
ISSN (elektroninen)1650-3740

Conference

ConferenceNORDIC CONFERENCE ON COMPUTATIONAL LINGUISTICS
LyhennettäNoDaLiDa
Maa/AlueRuotsi
KaupunkiGothenburg
Ajanjakso22/05/201724/05/2017

Sormenjälki

Sukella tutkimusaiheisiin 'Acoustic Model Compression with MAP adaptation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä