Speaker Adaptation for Multichannel End-to-End Speech Recognition.
Tsubasa OchiaiShinji WatanabeShigeru KatagiriTakaaki HoriJohn R. HersheyPublished in: ICASSP (2018)
Keyphrases
- end to end
- speaker adaptation
- speech recognition
- speaker independent
- speech recognizer
- hidden markov models
- automatic speech recognition
- speech signal
- linear prediction
- speaker dependent
- pattern recognition
- language model
- speech synthesis
- single channel
- multi channel
- speaker identification
- neural network
- maximum likelihood
- machine learning
- feature vectors
- natural language