Login / Signup
Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data.
Yerbolat Khassanov
Haihua Xu
Van Tung Pham
Zhiping Zeng
Eng Siong Chng
Chongjia Ni
Bin Ma
Published in:
INTERSPEECH (2019)
Keyphrases
</>
end to end
speech recognition
machine learning
noisy environments
speech processing
computer vision
pattern recognition
language model
speech signal
binary codes
speaker identification
speech recognizer
audio visual speech recognition