On the joint use of noise reduction and MLLR adaptation for in-car hands-free speech recognition.
Marco MatassoniMaurizio OmologoAlfiero SantarelliPiergiorgio SvaizerPublished in: ICASSP (2002)
Keyphrases
- noise reduction
- speaker adaptation
- speech recognition
- hands free
- automatic speech recognition
- noisy environments
- speaker independent
- signal to noise ratio
- edge preserving
- edge detection
- eye gaze
- user interface
- language model
- user friendly
- speech recognizer
- noise removal
- speech signal
- maximum likelihood
- speaker identification
- noise level
- hidden markov models
- speech synthesis
- pattern recognition
- wiener filter
- face tracking
- speech enhancement
- speech recognition systems
- broadcast news
- text entry
- feature extraction
- additive noise
- neural network
- image analysis
- generative model