A comparison of end-to-end models for long-form speech recognition.
Chung-Cheng ChiuWei HanYu ZhangRuoming PangSergey KishchenkoPatrick NguyenArun NarayananHank LiaoShuyuan ZhangAnjuli KannanRohit PrabhavalkarZhifeng ChenTara N. SainathYonghui WuPublished in: CoRR (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- acoustic models
- speech recognition technology
- speech signal
- pattern recognition
- speech synthesis
- speech processing
- speech recognizer
- automatic speech recognition
- noisy environments
- speech retrieval
- speaker identification
- congestion control
- language model
- probabilistic model
- neural network
- speech recognizers
- speaker dependent
- motion estimation
- feature extraction