Audio-Visual Speaker Tracking: Progress, Challenges, and Future Directions.
Jinzheng ZhaoYong XuXinyuan QianDavide BerghiPeipei WuMeng CuiJianyuan SunPhilip J. B. JacksonWenwu WangPublished in: CoRR (2023)
Keyphrases
- audio visual
- future directions
- lessons learned
- current challenges
- audio visual speech recognition
- open questions
- multi modal
- speaker verification
- visual information
- multi stream
- emotion recognition
- advanced technologies
- person authentication
- case study
- multimedia
- current status
- visual data
- sound source
- audio features
- search engine
- image classification
- feature selection