Speaker dependent bottleneck layer training for speaker adaptation in automatic speech recognition.
Rama DoddipatlaMadina HasanThomas HainPublished in: INTERSPEECH (2014)
Keyphrases
- speaker adaptation
- automatic speech recognition
- speaker dependent
- speech recognition
- phoneme recognition
- speech signal
- maximum likelihood
- speaker independent
- hidden markov models
- speaker identification
- broadcast news
- speech recognizer
- pattern recognition
- acoustic features
- noisy environments
- speech corpus
- neural network
- noisy images
- image processing