Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR.
Leda SariNiko MoritzTakaaki HoriJonathan Le RouxPublished in: CoRR (2020)
Keyphrases
- end to end
- speaker adaptation
- automatic speech recognition
- speech recognition
- speech signal
- speaker dependent
- hidden markov models
- broadcast news
- speaker independent
- speech recognizer
- noisy environments
- admission control
- maximum likelihood
- high bandwidth
- pattern recognition
- congestion control
- application layer
- speech synthesis
- language model
- neural network
- text localization and recognition
- audio visual
- transport layer
- non stationary