Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition

By Xue Feng, Yaodong Zhang, James R. Glass. 2014

216 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, 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 Representation & Self-Supervised Learning

In Speech & Audio

In Signal Processing

Citations in the corpus

SoundStream: An End-to-End Neural Audio Codec (2021, methodology): “Audio enhancement – Deep neural networks have been applied to different audio enhancement tasks, ranging from denoising [17]–[21] to dereverberation [22], [23], lossy coding denoising [2] and frequency bandwidth extension [1], [24].”
SEANet: A Multi-modal Speech Enhancement Network (2020, methodology): “Early works include methods based on denoising auto-encoders [8] and recurrent models [9].”
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition (2017, methodology): “Besides the conventional enhancement techniques [3], deep neural networks have been widely adopted to either directly reconstruct clean speech [7, 8] or estimate masks [9, 10, 11] from the noisy signals.”
Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition (2018, background): “To alleviate this issue, some robust ASR research focuses on mapping the out-of-domain data to in-domain data using enhancementbased methods [5, 6, 7], which generally requires parallel data from both domains.”
Deep Learning for Audio Signal Processing (2019, methodology): “Besides conventional enhancement techniques [129], deep neural networks have been widely adopted to either directly reconstruct clean speech [132], [133] or estimate masks [134]–[136] from”
Deep neural network based spectral feature mapping for robust speech recognition (2015, methodology): “Most previous work focused on learning clean version of MFCC using either denoising autoencoders [12, 13] or RNNs [14].”
Deep Learning for Environmentally Robust Speech Recognition (2017, methodology): “. 2nd CHiME log power [69] DBM add. TIMIT [71] DBM add. Aurora-2 mel [68] DSAE add. Japan. speech logMel [73] DBM con. CENSREC-4 [80] LSTM-DRNN add.&con. 2nd CHiME [42] LSTM-DRNN con. REVERB MFCC [74] SDAE add.&con. 2nd CHiME [12] DRNN add. Aurora-2 [77] LSTM-RNN add. Buckeye [79] LSTM-RNN c”
A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis (2016, methodology): “Deep auto-encoder based bottleneck features have been used by several groups for ASR [15, 16] and a deep denoising autoencoder has also verified for noise-robust ASR [17] or reverberant ASR tasks [18, 19].”
Cycle-Consistent Speech Enhancement (2018, methodology): “To deal with this problem, the feature mapping approach [12, 13, 14, 15, 16, 17] was proposed to train a mapping network that directly transforms the noisy features to”
Audio-visual speech recognition using deep learning (2014, background): “However, advances in deep learning research have led to recent breakthroughs in unsupervised audio feature extraction methods and exceptional recognition performance improvements [13, 17, 32].”
Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature (2015, methodology): “Since the dereverberation using the DAE is performed not on the STFT level ([10]) but the feature level ([11, 12]) in our system, we can feed the DAE output to the DNN-HMM acoustic model without any feature extraction process.”