Enhanced speech yielding higher intelligibility for all listeners and environments.
Takayuki AraiNao HodoshimaPublished in: INTERSPEECH (2010)
Keyphrases
- speech recognition
- dynamic environments
- speech synthesis
- speech signal
- real world
- text to speech
- speech recognizer
- language model
- automatic speech recognition
- linear prediction
- noisy environments
- lower levels
- speech processing
- multi lingual
- speaker verification
- higher quality
- signal to noise ratio
- multi agent systems