An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition.
Xuankai ChangTakashi MaekakuPengcheng GuoJing ShiYen-Ju LuAswin Shanmugam SubramanianTianzi WangShu-Wen YangYu TsaoHung-yi LeeShinji WatanabePublished in: CoRR (2021)
Keyphrases
- end to end
- speech recognition
- language model
- hidden markov models
- speech signal
- automatic speech recognition
- speech synthesis
- pattern recognition
- speech processing
- speech recognizer
- speech recognition technology
- speaker identification
- congestion control
- speech recognition systems
- noisy environments
- machine learning
- neural network
- information retrieval
- speech retrieval