Multi-level attention network: Mixed time–frequency channel attention and multi-scale self-attentive standard deviation pooling for speaker recognition
Lihong Deng, Fei Deng, Kepeng Zhou, Peifan Jiang, Gexiang Zhang, Qiang Yang, Qiang Yang
Topics & Concepts
Computer scienceDiscriminative modelPoolingSpeech recognitionFeature (linguistics)Pattern recognition (psychology)Frame (networking)Artificial intelligenceTelecommunicationsLinguisticsPhilosophySpeech Recognition and SynthesisMusic and Audio ProcessingSpeech and Audio Processing