Words on lips: How to merge acoustic and articulatory informations to automatic speech recognition.
Régine André-ObrechtBruno JacobChristine SénacPublished in: EUSIPCO (1996)
Keyphrases
- automatic speech recognition
- speech recognition
- acoustic features
- speech recognition systems
- speech sounds
- vocal tract
- speech segments
- spoken words
- speech signal
- word recognition
- word error rate
- speech corpus
- conversational speech
- visual speech
- recognition errors
- formant frequencies
- speech recognizers
- spontaneous speech
- hidden markov models
- speech synthesis
- acoustic models
- compound words
- broadcast news
- speaker independent
- speech retrieval
- noisy environments
- language model
- pattern recognition
- speech recognizer
- machine learning
- speaker identification
- n gram
- linear prediction
- image acquisition
- information retrieval
- word segmentation