Exploiting multimodal data fusion in robust speech recognition.
Panikos HeracleousPierre BadinGérard BaillyNorihiro HagitaPublished in: ICME (2010)
Keyphrases
- data fusion
- speech recognition
- noisy environments
- information fusion
- hidden markov models
- language model
- multi sensor
- speech synthesis
- speech processing
- automatic speech recognition
- fusion method
- fusion algorithm
- multi sensor data fusion
- speech recognizer
- multiple sensors
- speech recognition systems
- fusion methods
- multi source
- pattern recognition
- speech recognition technology
- speech signal
- image fusion
- situation assessment
- speaker identification
- speaker independent
- speech retrieval
- speech recognizers
- data mining
- low level
- digit recognition
- speaker adaptation
- multiscale