DEEPTALK: Vocal Style Encoding for Speaker Recognition and Speech Synthesis.
Anurag ChowdhuryArun RossPrabu DavidPublished in: ICASSP (2021)
Keyphrases
- speaker recognition
- speech synthesis
- speech recognition
- speech signal
- vocal tract
- speaker identification
- hidden markov models
- automatic speech recognition
- noisy environments
- language model
- gaussian mixture model
- pattern recognition
- text to speech
- sound source
- probabilistic neural network
- speaker verification
- vector quantization