End-to-End Automatic Speech Recognition Integrated with CTC-Based Voice Activity Detection.
Takenori YoshimuraTomoki HayashiKazuya TakedaShinji WatanabePublished in: ICASSP (2020)
Keyphrases
- end to end
- automatic speech recognition
- voice activity detection
- speech recognition
- noisy environments
- speech signal
- hidden markov models
- speech retrieval
- word error rate
- congestion control
- broadcast news
- admission control
- conversational speech
- spoken words
- language model
- recognition errors
- scalable video
- word recognition
- speech synthesis
- spontaneous speech
- transport layer
- image quality
- differentiated services
- speaker adaptation
- speech corpus
- speech sounds