Audio-visual automatic speech recognition and related bimodal speech technologies: A review of the state-of-the-art and open problems.
Gerasimos PotamianosPublished in: ASRU (2009)
Keyphrases
- audio visual
- open problems
- automatic speech recognition
- speech recognition
- multidatabase transaction management
- multi modal
- speech signal
- broadcast news
- word error rate
- hidden markov models
- multi stream
- conversational speech
- visual information
- acoustic features
- speaker verification
- visual data
- noisy environments
- emotion recognition
- audio visual speech recognition
- recognition errors
- speech sounds
- speech corpus
- multimedia
- spontaneous speech
- speech retrieval
- speaker identification
- spoken words
- computer vision
- audio features
- language model
- machine learning
- speech synthesis
- sound source
- non stationary
- database systems
- image processing