Environmental conditions and acoustic transduction in hands-free speech recognition.
Maurizio OmologoPiergiorgio SvaizerMarco MatassoniPublished in: Speech Commun. (1998)
Keyphrases
- environmental conditions
- speech recognition
- hands free
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- user interface
- user friendly
- hidden markov models
- noisy speech
- speech signal
- automatic speech recognition
- speech recognizer
- eye gaze
- text entry
- acoustic features
- pattern recognition
- language model
- dynamic environments
- speaker identification
- speech synthesis
- speech recognition technology
- noisy environments
- error rate
- face tracking
- face recognition
- information retrieval
- mobile phone
- mel frequency cepstral coefficients
- speaker diarization
- eye tracking
- eye movements
- human computer interaction
- multi modal
- multi view