Speech-XLNet: Unsupervised Acoustic Model Pretraining for Self-Attention Networks.
Xingchen SongGuangsen WangYiheng HuangZhiyong WuDan SuHelen MengPublished in: INTERSPEECH (2020)
Keyphrases
- unsupervised learning
- speech recognition
- data driven
- social networks
- semi supervised
- complex systems
- heterogeneous networks
- automatic speech recognition
- computer networks
- visual attention
- supervised learning
- real time
- active learning
- network model
- audio visual
- supervised classification
- pairwise
- pattern recognition
- speech synthesis
- completely unsupervised