Tibetan-Mandarin bilingual speech recognition based on end-to-end framework.

Qingnan Wang Wu Guo Peixin Chen Yan Song

Published in: APSIPA (2017)

Keyphrases

speech recognition
end to end
hidden markov models
automatic speech recognition
language model
speech recognizer
pattern recognition
speech signal
congestion control
speaker independent
speech processing
speech synthesis
neural network
information retrieval
noisy environments
speech retrieval