Lightly supervised GMM VAD to use audiobook for speech synthesiser.
Yoshitaka MamiyaJunichi YamagishiOliver WattsRobert A. J. ClarkSimon KingAdriana StanPublished in: ICASSP (2013)
Keyphrases
- voice activity detection
- noisy environments
- speaker recognition
- speech recognition
- gaussian mixture model
- learning algorithm
- semi supervised
- speaker identification
- supervised learning
- speaker verification
- speech signal
- unsupervised learning
- supervised classification
- feature selection
- automatic speech recognition
- noise reduction
- vector quantization
- unsupervised methods
- language model