Speech synthesis enhancement in noisy environments.
Davide BonardoEnrico ZovatoPublished in: INTERSPEECH (2007)
Keyphrases
- speech synthesis
- noisy environments
- speech recognition
- speech signal
- automatic speech recognition
- hidden markov models
- prosodic features
- speaker verification
- digit recognition
- background noise
- vocal tract
- language model
- speech enhancement
- pattern recognition
- speaker identification
- text to speech
- image enhancement
- voice activity detection
- image processing
- noise reduction
- speech corpus
- signal processing
- class noise
- data mining
- noisy speech
- signal to noise ratio
- subband
- image compression
- markov random field
- multiresolution
- neural network