LSTM-convolutional-BLSTM encoder-decoder network for minimum mean-square error approach to speech enhancement
Zeyu Wang, Tao Zhang, Yangyang Shao, Biyun Ding
Topics & Concepts
Computer scienceSpeech recognitionSpeech enhancementMinimum mean square errorConvolutional neural networkEncoderIntelligibility (philosophy)Artificial intelligenceDeep learningPattern recognition (psychology)AlgorithmNoise reductionMathematicsStatisticsEstimatorOperating systemEpistemologyPhilosophySpeech and Audio ProcessingSpeech Recognition and SynthesisAdvanced Adaptive Filtering Techniques