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...
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 |
Similar Items
-
Selection of acoustic modeling unit for Tibetan speech recognition based on deep learning
by: Gong Baojia, et al.
Published: (2021-01-01) -
End-to-End Amdo-Tibetan Speech Recognition Based on Knowledge Transfer
by: Xiaojun Zhu, et al.
Published: (2020-01-01) -
Tibetan speech synthesis based on an improved neural network
by: Ding Yuntao, et al.
Published: (2021-01-01) -
Tibetan interrogative sentence recognition and classification based on phrase features
by: Ban Mabao, et al.
Published: (2021-01-01) -
The Product of Language Contact Sentence Structure in the Hezhou Chinese Dialect and the Amdo Tibetan Dialect
by: Rigzin Wangmo, et al.
Published: (2009-10-01)