DNN based multi-speaker speech synthesis with temporal auxiliary speaker ID embedding.
Junmo LeeKwang-Sub SongKyoung Jin NohTae-Jun ParkJoon-Hyuk ChangPublished in: ICEIC (2019)
Keyphrases
- speech synthesis
- prosodic features
- speech recognition
- vocal tract
- text to speech
- speaker verification
- speaker recognition
- audio visual
- automatic speech recognition
- speaker identification
- temporal constraints
- spatial and temporal
- speaker dependent
- training process
- noisy environments
- language model
- speaker adaptation
- speech signal
- temporal reasoning
- speaker diarization
- information retrieval
- speech corpus
- temporal data
- temporal patterns
- vector space
- bayesian networks