Speaker-dependent Wavenet-based Delay-free Adpcm Speech Coding.
Takenori YoshimuraKei HashimotoKeiichiro OuraYoshihiko NankakuKeiichi TokudaPublished in: ICASSP (2019)
Keyphrases
- speaker dependent
- speech recognition
- phoneme recognition
- speaker identification
- speaker independent
- speech signal
- hidden markov models
- speaker recognition
- linear prediction
- broadcast news
- automatic speech recognition
- gaussian mixture model
- speech recognizer
- language model
- machine learning
- noisy environments
- audio signal
- speech recognition systems
- multi modal