A deep neural network for time-domain signal reconstruction

By Yuxuan Wang, Deliang Wang. 2015

107 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computational Mechanics, Model Architectures, 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 Cognitive Neuroscience

In Computational Mechanics

In Model Architectures

In Signal Processing

Citations in the corpus

Speech Denoising with Deep Feature Losses (2018, background): “This issue can be alleviated somewhat, but with increased computational cost and system complexity [12, 13, 14, 15, 16, 17, 18].”
Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, positive): “In simulated room responses with noise, cRM STOI improvements over TDR and RM are statistically significant.”
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction (2018, background): “A follow-up work [19] of [23] supplies clean phase during training.”
A New Framework for CNN-Based Speech Enhancement in the Time Domain (2019, methodology): “A similar approach of incorporating such domain knowledge inside the network is found to be useful in [10], which employs a”
Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks (2016, methodology): “Recently there has been a strong interest towards statistical-based methods using a deep neural network (DNN) [5, 6, 7, 8].”
Learning Complex Spectral Mapping with Gated Convolutional Recurrent Networks for Monaural Speech Enhancement (2019, methodology): “[33] K. Tan and D. L. Wang, “Complex spectral mapping with a convolutional recurrent network for monaural speech enhancement,” in Proc.”
Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, background): “acoustic parameters extracted from noisy speech to parameters describing the underlying clean data [5]–[9].”
Multichannel music separation with deep neural networks (2016, unknown): “The DNNs can be used either to predict the source spectrograms [5]–[8] whose ratio yields a time-frequency (TF) mask or directly to predict a TF mask [9]–[13].”
Complex Ratio Masking for Monaural Speech Separation (2015, methodology): “In fact, recent methods have shown that incorporating some phase information is beneficial [12], [13].”
DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement (2020, background): “Although many recent approaches have been proposed for phase reconstruction to address this issue [18, 19], the neural network remains real-valued.”
Multichannel Audio Source Separation With Deep Neural Networks (2016, background): “Various DNN architectures and training criteria have been investigated and compared [19], [21], [22].”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “Furthermore, to alleviate the adverse effects of using the phase of reverberant-noisy speech in resynthesizing the waveform signal of enhanced speech, this study extends the time-domain signal reconstruction technique in [182].”
Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network (2018, methodology): “The first network is a DNN which is trained using the MMSE criteria between enhanced and clean T-F spectrum.”
Deep Learning for Environmentally Robust Speech Recognition (2017, methodology): “f. Section III-A). Employingthe SA based objective function was empirically examined to perform better than the MA-based one for source separation [91]. Furthermore, the conclusions found in [91] and [98] indicate that combining the two objective functions (i.e., MA and SA) can further improve the s”
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech (2016, unknown): “Recently there has been a strong interest towards methods using a deep neural network (DNN) [5, 6, 7, 8, 9] to generate enhanced acoustic parameters from acoustic parameters extracted from noisy speech.”