Combined Vector Based on Factorized Time-delay Neural Network for Text-Independent Speaker Recognition.
Tianyu LiangYi LiuCan XuXianwei ZhangLiang HePublished in: Odyssey (2020)
Keyphrases
- object recognition
- recognition accuracy
- recognition rate
- automatic recognition
- pattern recognition
- feature extraction
- shape recognition
- information systems
- feature vectors
- data sets
- visual recognition
- character recognition
- recognition algorithm
- activity recognition
- neural network
- recognition engine
- handwritten numerals
- vector space
- image matching
- missing data
- image processing
- knowledge base
- artificial intelligence
- data mining