Adapting End-to-End Speech Recognition for Readable Subtitles.
Danni LiuJan NiehuesGerasimos SpanakisPublished in: IWSLT (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- speech recognizer
- speech synthesis
- pattern recognition
- speech processing
- noisy environments
- congestion control
- isolated word
- speech recognition systems
- speaker identification
- speech recognizers
- neural network
- speaker dependent
- computer vision
- speaker diarization
- signal processing
- speaker independent