Stream weight estimation using higher order statistics in multi-modal speech recognition.
Kazuto UkaiSatoshi TamuraSatoru HayamizuPublished in: AVSP (2015)
Keyphrases
- multi modal
- speech recognition
- higher order statistics
- hidden markov models
- language model
- automatic speech recognition
- pattern recognition
- correlation coefficient
- speech signal
- gaussian distribution
- speaker identification
- independent component analysis
- audio visual
- image statistics
- high dimensional
- probability density function
- maximum likelihood
- video search
- speech recognition systems
- multiscale
- probabilistic model
- speaker diarization