Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation.
Yoshiki MasuyamaXuankai ChangWangyou ZhangSamuele CornellZhong-Qiu WangNobutaka OnoYanmin QianShinji WatanabePublished in: WASPAA (2023)
Keyphrases
- learning process
- learning algorithm
- multiple representations
- visual recognition
- learning systems
- visual learning
- recognition engine
- language acquisition
- unsupervised learning
- learning tasks
- data integration
- audio visual
- recognition accuracy
- speech recognition
- hidden markov models
- object recognition
- pattern recognition
- reinforcement learning
- feature extraction
- decision trees