Transound: Hyper-head attention transformer for birds sound recognition
Quan Tang, Liming Xu, Bochuan Zheng, Chunlin He
Topics & Concepts
Mel-frequency cepstrumComputer scienceArtificial intelligenceDiscrete cosine transformENCODETransformerPattern recognition (psychology)Feature vectorSpeech recognitionOptical flowFeature extractionComputer visionEngineeringElectrical engineeringImage (mathematics)ChemistryVoltageGeneBiochemistryAnimal Vocal Communication and BehaviorMusic and Audio ProcessingAnimal Behavior and Welfare Studies