Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets.
Zhenning TanYuguang YangEunjung HanAndreas StolckePublished in: ASRU (2021)
Keyphrases
- speaker identification
- speech recognition
- speaker recognition
- gaussian mixture model
- speaker dependent
- speech signal
- probabilistic neural network
- noisy environments
- feature extraction
- language identification
- feature transformation
- broadcast news
- speaker independent
- automatic speech recognition
- speaker diarization
- audio features
- low dimensional
- image segmentation
- image processing
- noise reduction
- mixture model
- maximum likelihood
- pattern recognition