Lightweight Speaker Verification Using Transformation Module With Feature Partition and Fusion.
Yanxiong LiZhongjie JiangQisheng HuangWenchang CaoJialong LiPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- lightweight
- speaker verification
- score normalization
- noisy environments
- speaker recognition
- prosodic features
- audio visual
- data fusion
- using artificial neural networks
- person authentication
- feature vectors
- computer vision
- multilayer perceptron
- emotion recognition
- image features
- development environments
- communication infrastructure
- non stationary
- information fusion
- genetic algorithm
- face verification
- feature set
- wireless sensor networks