A Comparison of End-to-End Models for Long-Form Speech Recognition.
Chung-Cheng ChiuAnjuli KannanRohit PrabhavalkarZhifeng ChenTara N. SainathYonghui WuWei HanYu ZhangRuoming PangSergey KishchenkoPatrick NguyenArun NarayananHank LiaoShuyuan ZhangPublished in: ASRU (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- probabilistic model
- pattern recognition
- language model
- automatic speech recognition
- speaker identification
- acoustic models
- congestion control
- speech signal
- speech synthesis
- speech recognizer
- computational complexity
- speech recognition systems
- noisy environments
- mixture model
- speaker dependent