X-TF-GridNet: A time–frequency domain target speaker extraction network with adaptive speaker embedding fusion
Fengyuan Hao, Xiaodong Li, Chengshi Zheng
Topics & Concepts
Computer scienceDiscriminative modelSpeech recognitionEmbeddingSpeaker recognitionSpeaker diarisationExtractorKey (lock)Quality (philosophy)Pattern recognition (psychology)Artificial intelligencePhilosophyEpistemologyEngineeringProcess engineeringComputer securitySpeech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and Synthesis