Data collection in real acoustical environments for sound scene understanding and hands-free speech recognition.
Satoshi NakamuraKazuo HiyaneFutoshi AsanoTakeshi YamadaTakashi EndoPublished in: EUROSPEECH (1999)
Keyphrases
- speech recognition
- scene understanding
- data collection
- object detection
- object recognition
- hidden markov models
- hands free
- d scene
- vision system
- language model
- automatic speech recognition
- pattern recognition
- speech signal
- video surveillance
- speech recognition systems
- speaker identification
- markov random field
- multi view
- probabilistic model
- user friendly
- face recognition
- eye gaze
- neural network