Adaptive Stream Fusion in Multistream Recognition of Speech.
Nima MesgaraniSamuel ThomasHynek HermanskyPublished in: INTERSPEECH (2011)
Keyphrases
- recognition engine
- human face recognition
- recognition rate
- multi stream
- speech recognition
- speech corpus
- continuous speech recognition
- automatic recognition
- object recognition
- recognition accuracy
- automatic speech recognition systems
- spoken words
- phoneme recognition
- audio stream
- speech signal
- automatic speech recognition
- digit recognition
- activity recognition
- sliding window
- data streams
- feature extraction
- real time
- data fusion
- facial gestures
- recognition algorithm
- multimodal biometrics
- human activities
- speaker dependent
- video sequences