2015 · 10 citations · 17 references
ComputingComputer ScienceAcousticsComputational AcousticsMachine LearningDeep LearningNoiseNoise ReductionPattern RecognitionSpeech AcousticsSpeech RecognitionAdditive NoiseConvolutional Neural NetworksDeep Neural Network Acoustic ModelsEqual Error RateNoise RobustnessRobust Speech RecognitionSpeech Recognition AcousticsWord Recognition In Noise
One of the biggest challenges in speech recognition today is its use on a daily basis, in which distortion and noise in the environment are present and hinder the recognition task. In the last thirty years, hundreds of methods for noise-robust recognition were proposed, each with its own advantages and disadvantages. In this paper, the use of convolutional neural networks (CNN) as acoustic models in automatic speech recognition systems (ASR) is proposed as an alternative to the classical recognition methods based on HMM without any noise-robust method applied. The experiment showed that the presented method reduces the equal error rate in word recognition tasks with additive noise.
17
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text