Progressive Multi-Target Network Based Speech Enhancement with Snr-Preselection for Robust Speaker Diarization.
Lei SunJun DuXueyang ZhangTian GaoXin FangChin-Hui LeePublished in: ICASSP (2020)
Keyphrases
- speech enhancement
- noisy environments
- multi target
- speaker diarization
- signal to noise ratio
- noise reduction
- speaker identification
- speech signal
- speech recognition
- speaker verification
- single channel
- visual tracking
- multi target tracking
- multi sensor
- multi camera
- model selection
- bayesian information criterion
- multiple targets
- information retrieval