Speaker Extraction With Co-Speech Gestures Cue.
Zexu PanXinyuan QianHaizhou LiPublished in: IEEE Signal Process. Lett. (2022)
Keyphrases
- speech recognition
- automatic speech recognition
- speaker recognition
- audio visual
- hidden markov models
- speaker verification
- spoken words
- speaker identification
- speech signal
- speaker dependent
- vocal tract
- prosodic features
- hand movements
- automatic speech recognition systems
- speaker diarization
- gesture recognition
- automatic extraction
- broadcast news
- hand gestures
- gaussian mixture model
- multi modal
- information extraction
- human communication
- speech synthesis
- acoustic features
- sign language
- phoneme recognition
- probabilistic neural network
- automatic transcription
- speaker independent
- acoustic models
- audio stream
- text to speech
- noisy environments
- language model
- feature extraction
- spontaneous speech
- speech recognizer
- neural network
- human robot interaction
- visual data
- speech sounds
- feature vectors