Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions.
Dipjyoti PaulYannis PantazisYannis StylianouPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- speaker verification
- automatic speech recognition
- speaker diarization
- sufficient conditions
- neural network
- language model
- network architecture
- bio inspired
- speaker identification
- support vector
- artificial intelligence
- database
- prosodic features
- multiscale
- machine learning