Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks.
Xingcheng SongGuangsen WangZhiyong WuYiheng HuangDan SuDong YuHelen MengPublished in: CoRR (2019)
Keyphrases
- semi supervised
- unsupervised learning
- network analysis
- speech recognition
- complex networks
- social networks
- pattern recognition
- endpoint detection
- machine learning
- automatic speech recognition
- speech signal
- visual attention
- supervised learning
- network design
- focus of attention
- network size
- information transfer
- pairwise