Self-Attention Transducers for End-to-End Speech Recognition.
Zhengkun TianJiangyan YiJianhua TaoYe BaiZhengqi WenPublished in: INTERSPEECH (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- automatic speech recognition
- speech recognizer
- congestion control
- speech signal
- speech synthesis
- speech processing
- pattern recognition
- speaker identification
- speech recognition systems
- speech recognition technology
- speech recognizers
- noisy environments
- speaker independent
- speech retrieval
- machine learning
- word segmentation
- speaker adaptation
- isolated word
- digital video library