DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders.
Yanqing LiuRuiqing XueLei HeXu TanSheng ZhaoPublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- speech synthesis
- vector quantized
- vector quantization
- speech recognition
- image compression
- progressive transmission
- text to speech
- visual words
- video compression
- congestion control
- vector quantizer
- error propagation
- image coding
- bag of words
- compression scheme
- optical flow
- image classification
- hidden markov models