Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information.
Chi-Luen FengPo-chun HsuHung-yi LeePublished in: CoRR (2022)
Keyphrases
- computational model
- speech recognition
- partial information
- high level
- probabilistic model
- information extraction
- mathematical model
- context dependent
- expert knowledge
- speaker diarization
- neural network
- missing information
- statistical information
- information sharing
- information sources
- conceptual model
- speech signal
- automatic speech recognition
- experimental data
- bayesian information criterion
- artificial neural networks