An investigation of deep neural networks for noise robust speech recognition

By M. Seltzer, Dong Yu, Yongqiang Wang. 2013

694 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

In Speech & Audio

In Signal Processing

Citations in the corpus

Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training (2021, background): “It is well known that the performance of ASR systems trained from scratch with conventional supervised objectives can degrade significantly when tested on domains mismatched from training data [7, 8].”
Dropout Improves Recurrent Neural Networks for Handwriting Recognition (2013, background): “It is shown to be effective with deep convolutional networks [12], [13], [14], feed-forward networks [15], [16], [17] but, to the best of our knowledge, has never been applied to RNNs.”
Deep Learning: Methods and Applications (2014, methodology): “[325], who applied the C-MMSE [415] feature enhancement algorithm on the input feature”
Highway long short-term memory RNNS for distant speech recognition (2015, background): “Recently the deep neural network (DNN)-based acoustic models (AMs) greatly improved automatic speech recognition (ASR) accuracy on many tasks [1, 2, 3, 4].”
Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition (2018, background): “Another popular strategy is to train an ASR system with as large, and as diverse a dataset as possible [8, 9]; however, this strategy is not feasible when the labeled data are not available for all domains.”
Speech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks (2016, methodology): “[20] called it noise-aware training of DNN.”
Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement (2017, methodology): “Dropout [39] and static noise aware training as in [12, 40] were used to improve its generalization capacity for unseen noise environments.”
Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home (2017, background): “Recent advances in deep-learning techniques and the availability of large training databases have resulted in significant improvements in speech recognition accuracy [1, 2, 3, 4].”
Hybrid acoustic models for distant and multichannel large vocabulary speech recognition (2013, background): “We attribute this to the fact that multiple layers of non-linear transformations can better compensate against small variabilities in feature space [32].”
New Era for Robust Speech Recognition (2017, methodology): “Note that although in the discussion we assumed no additive noise, the WPE algorithm has been shown to perform well in the presence of noise [12, 45, 48] and to be effective for meeting recognition [21, 47].”
LINEAR PREDICTION-BASED DEREVERBERATION WITH ADVANCED SPEECH ENHANCEMENT AND RECOGNITION TECHNOLOGIES FOR THE REVERB CHALLENGE (2014, methodology): “For unsupervised batch adaptation of the first layer of the DNNs, we performed a few backpropagation iterations assuming that the labels obtained from a first recognition pass were true references.”
Deep Learning for Environmentally Robust Speech Recognition (2017, methodology): “The widely used approach comes to multicondition training (Seltzer et al. 2013).”
Text-informed speech enhancement with deep neural networks (2015, neutral): “…the text features in a speech enhancement framework previously, DNN may al-Figure As shown in many literatures including TTS [12, 13], automatic speech recognition (ASR) [20–22] and enhancement research [23], the nature of DNN allows us to utilize disparate features jointly in an inference stage.”
A review on machine learning principles for multi-view biological data integration (2016, background): “Some experimental studies have reported that deep learning models are robust to noise [150, 151].”
Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks (2015, methodology): “Similar to a DNNHMM hybrid system[13, 14], we use HMM state ru,t at frame t in utterance u as a training target, which is obtained from the reference with the Viterbi alignment.”
Speaker adaptation of neural network acoustic models using i-vectors (2013, result): “Lastly, noise-aware DNNs proposed in [6], which use as input uncompensated features and time-dependent estimates of the noise, are also relevant to our work.”