On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers.
Shucong ZhangErfan LoweimiPeter BellSteve RenalsPublished in: CoRR (2020)
Keyphrases
- automatic speech recognition
- speech recognition
- hidden markov models
- speech signal
- conversational speech
- word error rate
- broadcast news
- speech retrieval
- noisy environments
- acoustic features
- recognition errors
- spoken words
- word recognition
- speech corpus
- spontaneous speech
- multiscale
- visual attention
- multi modal
- speaker adaptation