On using a priori segmentation of the speech signal in an N-best solutions post-processing.
Thierry MoudencDenis JouvetJean MonnéPublished in: ICASSP (1995)
Keyphrases
- post processing
- speech signal
- speech recognition
- preprocessing
- filtering method
- spectral analysis
- automatic speech recognition
- noisy environments
- image segmentation
- speaker identification
- post processed
- linear prediction
- multiscale
- background noise
- acoustic features
- hearing aids
- image quality
- language model
- speaker recognition
- hidden markov models
- automatic speech recognition systems