Recurrent neural networks for noise reduction in robust ASR

Abstract

Recent work on deep neural networks as acoustic models for automatic speech recognition (ASR) have demonstrated substantial performance improvements. We introduce a model which uses a deep recurrent auto encoder neural network to denoise input features for robust ASR. The model is trained on stereo (noisy and clean) audio features to predict clean features given noisy input. The model makes no assumptions about how noise affects the signal, nor the existence of distinct noise environments. Instead, the model can learn to model any type of distortion or additive noise given sufficient training data. We demonstrate the model is competitive with existing feature denoising approaches on the Aurora2 task, and outperforms a tandem approach where deep networks are used to predict phoneme posteriors directly.

Keywords

Noise reductionReduction (mathematics)Computer scienceNoise (video)Artificial neural networkSpeech recognitionRecurrent neural networkNoise measurementArtificial intelligenceMathematics

Affiliated Institutions

Related Publications

Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR

Oriol Vinyals , Suman Ravuri

In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of...

2011 55 citations

Deep Belief Networks using discriminative features for phone recognition

Abdelrahman Mohamed , Tara N. Sainath , George E. Dahl +3 more

Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fe...

2011 289 citations

A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures

Yong Yu , Xiaosheng Si , Changhua Hu +1 more

Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cel...

2019 Neural Computation 4793 citations

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

Geoffrey E. Hinton , Li Deng , Dong Yu +8 more

Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well ...

2012 IEEE Signal Processing Magazine 10065 citations

Learning the hidden structure of speech

Jeffrey L. Elman , David Zipser

In the work described here, the backpropagation neural network learning procedure is applied to the analysis and recognition of speech. This procedure takes a set of input/outpu...

1988 The Journal of the Acoustical Society... 269 citations

Publication Info

Year: 2012
Type: article
Citations: 337
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Recurrent neural networks for noise reduction in robust ASR

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

337

OpenAlex

Cite This

APA Style

                            
                                    Andrew L. Maas, 
                                
                                    Quoc V. Le, 
                                
                                    Tyler M. O'Neil
                                
                                et al.
                            
                            (2012). 
                            Recurrent neural networks for noise reduction in robust ASR. 
                            
                            .
                            https://doi.org/10.21437/interspeech.2012-6

Identifiers

DOI: 10.21437/interspeech.2012-6