2015 · 37 citations · 28 references
ComputingComputer ScienceFeature EngineeringMachine LearningNatural Language ProcessingDeep LearningNoise ReductionPattern RecognitionSpeech AcousticsSpeech RecognitionSpeech SynthesisMultichannel Speech EnhancementNoise RobustnessRestricted Boltzmann MachinesRobust Speech RecognitionSpeech EnhancementSpeech Enhancement AlgorithmsSpeech Enhancement For RecognitionSpeech Signal Enhancement
We consider the problem of robust automatic speech recognition (ASR) in the context of the CHiME-3 Challenge. The proposed system combines three contributions. First, we propose a deep neural network (DNN) based multichannel speech enhancement technique, where the speech and noise spectra are estimated using a DNN based regressor and the spatial parameters are derived in an expectation-maximization (EM) like fashion. Second, a conditional restricted Boltzmann machine (CRBM) model is trained using the obtained enhanced speech and used to generate simulated training and development datasets. The goal is to increase the similarity between simulated and real data, so as to increase the benefit of multicondition training. Finally, we make some changes to the ASR backend. Our system ranked 4th among 25 entries.
28
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations
Recurrent neural network based language model
Tomáš Mikolov, Martin Karafiát, Lukáš Burget et al. · 2010 · 5.4K citations
On the importance of initialization and momentum in deep learning
Ilya Sutskever, James Martens, George E. Dahl et al. · 2013 · 3.5K citations
Deep Learning: Methods and Applications
Li Deng, Dong Yu · Foundations and Trends® in Signal Processing · 2014 · 3.3K citations · Full text