Improvement of Acoustic Models Fused with Lip Visual Information for Low-Resource Speech.
Chongchong YuJiaqi YuZhaopeng QianYuchen TanPublished in: Sensors (2023)
Keyphrases
- visual information
- acoustic models
- speech recognition
- audio visual
- automatic speech recognition
- broadcast news
- speech recognizer
- hidden markov models
- visual features
- low level
- visual data
- speaker independent
- visual content
- speech signal
- discriminative training
- eye movements
- spoken language
- language model
- image collections
- speaker identification
- semantic information
- computer vision
- dialogue system
- audio features
- knowledge representation
- pattern recognition
- face recognition
- image processing