Adaptive fusion of acoustic and visual sources for automatic speech recognition.
Alexandrina RogozanPaul DeléglisePublished in: Speech Commun. (1998)
Keyphrases
- automatic speech recognition
- acoustic features
- speech recognition
- speech sounds
- speech recognizers
- speech signal
- speech segments
- speech retrieval
- acoustic models
- hidden markov models
- conversational speech
- visual features
- word error rate
- speech recognition systems
- broadcast news
- noisy environments
- spontaneous speech
- word recognition
- visual information
- recognition errors
- spoken words
- formant frequencies
- visual speech
- speech corpus
- speaker independent
- speech synthesis
- visual data
- image classification
- low level