Audio DistilBERT: A Distilled Audio BERT for Speech Representation Learning.
Fan YuJiawei GuoWei XiZhao YangRui JiangChao ZhangPublished in: IJCNN (2021)
Keyphrases
- audio visual
- audio stream
- audio signals
- broadcast news
- learning systems
- learning algorithm
- multimedia
- learning process
- signal processing
- knowledge acquisition
- learning tasks
- digital audio
- text to speech
- language acquisition
- emotion recognition
- machine learning
- online learning
- active learning
- feature selection
- learning mechanism
- visual information
- multi modal
- cross modal
- speaker identification
- hidden markov models
- reinforcement learning
- linear predictive coding
- cepstral features