Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-to-End ASR.
Leda SariNiko MoritzTakaaki HoriJonathan Le RouxPublished in: ICASSP (2020)
Keyphrases
- end to end
- speaker adaptation
- automatic speech recognition
- speech recognition
- speaker dependent
- hidden markov models
- speech signal
- speaker independent
- broadcast news
- admission control
- maximum likelihood
- high bandwidth
- congestion control
- language model
- speech synthesis
- transport layer
- pattern recognition
- speaker identification
- internet protocol
- noisy environments
- computer vision
- acoustic features
- speech recognition systems