Multi-Modal Acoustic-Articulatory Feature Fusion For Dysarthric Speech Recognition.
Zhengjun YueErfan LoweimiZoran CvetkovicHeidi ChristensenJon BarkerPublished in: ICASSP (2022)
Keyphrases
- multi modal
- speech recognition
- feature fusion
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- feature extraction
- acoustic features
- speech signal
- automatic speech recognition
- speech recognizer
- multiple features
- speech synthesis
- hidden markov models
- language model
- pattern recognition
- high dimensional
- audio visual
- sound source
- vocal tract
- image annotation
- speaker identification
- mel frequency cepstral coefficients
- video search
- neural network
- image segmentation
- machine learning