Multimodal fusion by adaptive compensation for feature uncertainty with application to audiovisual speech recognition.
Athanassios KatsamanisGeorge PapandreouVassilis PitsikalisPetros MaragosPublished in: EUSIPCO (2006)
Keyphrases
- speech recognition
- hidden markov models
- speech synthesis
- speech processing
- automatic speech recognition
- language model
- speech recognition technology
- pattern recognition
- speech signal
- noisy environments
- speaker identification
- speech recognizer
- feature vectors
- maximum likelihood
- image retrieval
- multimedia
- computer vision
- speech recognition systems
- artificial intelligence