Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets.
Zhenning TanYuguang YangEunjung HanAndreas StolckePublished in: CoRR (2021)
Keyphrases
- speaker identification
- speech recognition
- speaker recognition
- gaussian mixture model
- speech signal
- speaker dependent
- noisy environments
- language identification
- feature extraction
- feature transformation
- probabilistic neural network
- broadcast news
- speaker diarization
- speaker independent
- mel frequency cepstral coefficients
- automatic speech recognition
- dimensionality reduction
- hidden markov models
- low dimensional
- neural network