Adaptation of PLDA for multi-source text-independent speaker verification.
Liping ChenKong-Aik LeeBin MaLong MaHaizhou LiLi-Rong DaiPublished in: ICASSP (2017)
Keyphrases
- multi source
- speaker verification
- data fusion
- information fusion
- noisy environments
- language identification
- emotion recognition
- audio visual
- information retrieval
- data sources
- multiple sources
- community detection
- text mining
- data integration
- multi modal
- databases
- semantic information
- multilayer perceptron
- information extraction
- face verification
- keywords
- feature extraction