Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition.
George PapandreouAthanassios KatsamanisVassilis PitsikalisPetros MaragosPublished in: IEEE Trans. Speech Audio Process. (2009)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech recognizer
- automatic speech recognition
- speech recognition systems
- speech processing
- speech synthesis
- speech signal
- speaker independent
- speaker identification
- speaker dependent
- multimodal fusion
- high robustness
- computer vision
- high accuracy
- pattern recognition
- image sequences