A Regression Approach to Speech Enhancement Based on Deep Neural Networks

By Yong Xu, Jun Du, Lirong Dai, Chin-Hui Lee. 2015

1,344 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Speech & Audio

In Signal Processing

Citations in the corpus

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale (2023, background): “Voice conversion [27, 39], emotion conversion [53, 34], speech enhancement [63, 11, 55] belong to this category.”
Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders (2021, methodology): “Motivated by the performance of modern neural speech enhancers in removing unwanted noise and reverberation from audio signals [13, 14, 15, 16, 17], we combine the learning based compression and learning based enhancement paradigms.”
Speech Denoising with Deep Feature Losses (2018, background): “However, most pipelines still operate in the spectrogram domain [4, 5, 6, 7, 8, 9, 10, 11].”
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.”
A Wavenet for Speech Denoising (2017, background): “Similarly, most techniques for speech denoising use magnitude spectrograms as front-end [3, 4, 5].”
SEGAN: Speech Enhancement Generative Adversarial Network (2017, background): “In [15] and [16], noise features are estimated and included in the input features of deep neural networks.”
Real Time Speech Enhancement in the Waveform Domain (2020, background): “Over the last years, there has been a growing interest towards DNN based methods for speech enhancement [34, 35, 36, 37, 20, 38, 39, 22, 40, 7, 41, 8, 42, 21, 37].”
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (2018, methodology): “This process can be performed by directly approximating the spectrogram representation of each source from the mixture using nonlinear regression techniques, where the clean source spectrograms are used as the training target [2], [3], [4].”
A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement (2017, methodology): “Deep learning techniques are already being used for noise suppression [5], [6], [7], [8], [9].”
Sergan: Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty (2019, background): “Recently, deep neural network (DNN)-based approaches gained success in speech enhancement due to their powerful modeling capabilities [1–5].”
DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement (2020, background): “Hence, early studies only focus on magnitude related training target while ignoring phase [15–17], resynthesizing the estimated speech by simply applying estimated magnitude with the noisy speech phase.”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, neutral): “A prominent form of the TMS is the log-power spec- 494 trum normalized to zero mean and unit variance [197].”
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].”
A New Framework for CNN-Based Speech Enhancement in the Time Domain (2019, background): “popular deep learning methods are denoising autoencoders [4], feedforward neural networks [5], [6], and CNNs [7]–[9].”
Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, methodology): “In the work described in [6] authors train a feedforward neural network with noise-aware training and global variance estimation using more than 100 different noise conditions [10], both techniques seem to improve results.”
Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks (2017, methodology): “These 91 noises were a subset of the 104 noise types used in [69], [70].”
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.”