Weakly Supervised Target-Speaker Voice Activity Detection.
Zixin ZhaoLan ZhangPublished in: BIGCOM (2023)
Keyphrases
- input image
- weakly supervised
- superpixels
- voice activity detection
- speech recognition
- object class
- noisy environments
- topic models
- relation extraction
- named entities
- automatic speech recognition
- object detectors
- semi supervised
- target object
- information retrieval
- higher order
- viewpoint
- image retrieval
- object recognition