TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition.
Zhengkun TianJiangyan YiJianhua TaoYe BaiShuai ZhangZhengqi WenXuefei LiuPublished in: CoRR (2021)
Keyphrases
- speech recognition
- language model
- hidden markov models
- automatic speech recognition
- acoustic models
- speech synthesis
- pattern recognition
- speech recognizer
- speaker identification
- computer vision
- speech signal
- probabilistic model
- speaker recognition
- speech understanding
- feature vectors
- natural language
- speaker diarization