A language model for Amdo Tibetan speech recognition

We built a language model which is based on Transformer network architecture, used attention mechanisms to dispensing with recurrence and convalutions entirely. Through the transliteration of Tibetan to International Phonetic Alphabets, the language model was trained using the syllables and phonemes...

Full description

Bibliographic Details
Main Authors:	Suan Taiben, Cai Rangzhuoma, Cai Zhijie, Zu Ba, Gong Baojia
Format:	Article
Language:	English
Published:	EDP Sciences 2021-01-01
Series:	MATEC Web of Conferences
Online Access:	https://www.matec-conferences.org/articles/matecconf/pdf/2021/05/matecconf_cscns20_06016.pdf

id	doaj-c1d97ac2f9c747fe85248b1310a7457b
record_format	Article
spelling	doaj-c1d97ac2f9c747fe85248b1310a7457b2021-02-18T10:45:18ZengEDP SciencesMATEC Web of Conferences2261-236X2021-01-013360601610.1051/matecconf/202133606016matecconf_cscns20_06016A language model for Amdo Tibetan speech recognitionSuan TaibenCai RangzhuomaCai ZhijieZu BaGong BaojiaWe built a language model which is based on Transformer network architecture, used attention mechanisms to dispensing with recurrence and convalutions entirely. Through the transliteration of Tibetan to International Phonetic Alphabets, the language model was trained using the syllables and phonemes of the Tibetan word as modeling units to predict corresponding Tibetan sentences according to the context semantics of IPA. And it combined with the acoustic model as the Tibetan speech recognition was compared with end-to-end Tibetan speech recognition.https://www.matec-conferences.org/articles/matecconf/pdf/2021/05/matecconf_cscns20_06016.pdf
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Suan Taiben Cai Rangzhuoma Cai Zhijie Zu Ba Gong Baojia
spellingShingle	Suan Taiben Cai Rangzhuoma Cai Zhijie Zu Ba Gong Baojia A language model for Amdo Tibetan speech recognition MATEC Web of Conferences
author_facet	Suan Taiben Cai Rangzhuoma Cai Zhijie Zu Ba Gong Baojia
author_sort	Suan Taiben
title	A language model for Amdo Tibetan speech recognition
title_short	A language model for Amdo Tibetan speech recognition
title_full	A language model for Amdo Tibetan speech recognition
title_fullStr	A language model for Amdo Tibetan speech recognition
title_full_unstemmed	A language model for Amdo Tibetan speech recognition
title_sort	language model for amdo tibetan speech recognition
publisher	EDP Sciences
series	MATEC Web of Conferences
issn	2261-236X
publishDate	2021-01-01
description	We built a language model which is based on Transformer network architecture, used attention mechanisms to dispensing with recurrence and convalutions entirely. Through the transliteration of Tibetan to International Phonetic Alphabets, the language model was trained using the syllables and phonemes of the Tibetan word as modeling units to predict corresponding Tibetan sentences according to the context semantics of IPA. And it combined with the acoustic model as the Tibetan speech recognition was compared with end-to-end Tibetan speech recognition.
url	https://www.matec-conferences.org/articles/matecconf/pdf/2021/05/matecconf_cscns20_06016.pdf
work_keys_str_mv	AT suantaiben alanguagemodelforamdotibetanspeechrecognition AT cairangzhuoma alanguagemodelforamdotibetanspeechrecognition AT caizhijie alanguagemodelforamdotibetanspeechrecognition AT zuba alanguagemodelforamdotibetanspeechrecognition AT gongbaojia alanguagemodelforamdotibetanspeechrecognition AT suantaiben languagemodelforamdotibetanspeechrecognition AT cairangzhuoma languagemodelforamdotibetanspeechrecognition AT caizhijie languagemodelforamdotibetanspeechrecognition AT zuba languagemodelforamdotibetanspeechrecognition AT gongbaojia languagemodelforamdotibetanspeechrecognition
_version_	1724263135453380608

A language model for Amdo Tibetan speech recognition

Similar Items