Multi-channel speech enhancement using early and late fusion convolutional neural networks
S. Siva Priyanka, T. K. Satish Kumar
Topics & Concepts
TIMITConvolutional neural networkComputer scienceSpeech recognitionFusionChannel (broadcasting)GeneralizationNoise (video)Pattern recognition (psychology)Speech enhancementMicrophoneArtificial intelligenceAlgorithmMathematicsNoise reductionHidden Markov modelTelecommunicationsImage (mathematics)Mathematical analysisLinguisticsPhilosophySound pressureSpeech and Audio ProcessingAdvanced Adaptive Filtering TechniquesSpeech Recognition and Synthesis