SiamTDNN: Enhancing Discriminative Embeddings for Speaker Diarization.
Runqing ZhangHuijun LuDunbo CaiZhiguo HuangYujian DuLing QianYijun ZhangPublished in: J. Circuits Syst. Comput. (2024)
Keyphrases
- speaker diarization
- speech recognition
- low dimensional
- bayesian information criterion
- semi supervised
- feature extraction
- dimensionality reduction
- unsupervised learning
- high dimensional data
- feature selection
- broadcast news
- speaker verification
- computer vision
- bayesian networks
- image classification
- neural network
- gaussian mixture model
- speaker identification
- information retrieval