Hands-free speech recognition using blind source separation post-processed by two-stage spectral subtraction.
Masanori TsujikawaKen-ichi IsoPublished in: INTERSPEECH (2004)
Keyphrases
- blind source separation
- speech signal
- hands free
- post processed
- speech recognition
- post processing
- user interface
- user friendly
- non stationary
- eye gaze
- automatic speech recognition
- vocal tract
- face tracking
- noisy environments
- text entry
- independent component analysis
- speech enhancement
- hidden markov models
- eye tracker
- negative matrix factorization
- language model
- image processing
- eye tracking
- image segmentation
- machine learning
- eye movements
- pattern recognition
- edge detection
- computer vision
- information retrieval