Multi-user VoiceFilter-Lite via Attentive Speaker Embedding.
Rajeev RikhyeQuan WangQiao LiangYanzhang HeIan McGrawPublished in: CoRR (2021)
Keyphrases
- multi user
- virtual environment
- virtual world
- speech recognition
- augmented reality
- multiple users
- multi granularity
- single user
- user interface
- multi touch
- visual attention
- vector space
- audio visual
- pre attentive
- speaker verification
- graph embedding
- automatic speech recognition
- collaborative writing
- image processing
- three dimensional