Improvement of multimodal gesture and speech recognition performance using time intervals between gestures and accompanying speech.
Madoka MikiNorihide KitaokaChiyomi MiyajimaTakanori NishinoKazuya TakedaPublished in: EURASIP J. Audio Speech Music. Process. (2014)
Keyphrases
- speech recognition
- hidden markov models
- gesture recognition
- pointing gestures
- speech signal
- hand gestures
- speech synthesis
- multimodal interfaces
- speech recognizer
- automatic speech recognition
- human robot interaction
- multi stream
- speech processing
- speaker independent
- sign language
- hand movements
- speech recognition technology
- speech recognition systems
- pattern recognition
- multi modal
- speech recognizers
- recognition engine
- language model
- noisy environments
- word error rate
- keyword spotting
- speaker identification
- speaker dependent
- human computer interaction
- audio visual
- speech retrieval
- speech recognition errors
- maximum likelihood
- noisy speech
- information retrieval
- acoustic models
- speech enhancement
- vocal tract
- speaker diarization