An Experimental Study on Speech Enhancement Based on Deep Neural Networks

By Yong Xu, Jun Du, Lirong Dai, Chin-Hui Lee. 2014

926 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

Deep Learning: Methods and Applications (2014, background): “to emotion recognition from speech in [207, 222], to spoken language understanding in [242, 366, 403], to speaker recognition in [351, 372], to language-type recognition in [112], to dialogue state tracking for spoken dialogue systems in [94, 152], to automatic voice activity detection in [442], to ”
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition (2017, background): “They are crucial components, either explicitly [3] or implicitly [4, 5], in ASR systems for noise robustness.”
Bitwise Neural Networks (2016, background): “, 2012), speech enhancement (Xu et al., 2014), etc, it is also the case that the relatively bigger networks with more parameters than before call for more resources (processing power, memory, battery time, etc), which are sometimes critically constrained in applications running on embedded devices.”
SDR – Half-baked or Well Done? (2018, methodology): “Source separation and speech enhancement have been an intense focus of research in the signal processing community for several decades, and interest has gotten even stronger with the recent advent of powerful new techniques based on deep learning [1–11].”
Permutation invariant training of deep models for speaker-independent multi-talker speech separation (2016, background): “Typieally, networks are trained based on parallel sets of mixtures and their constituent target sources [19, 20, 21, 22].”
Deep clustering: Discriminative embeddings for segmentation and separation (2015, methodology): “In this paper, we propose a new partition-based approach which learns embeddings for each input elements, such that the correct labeling can be determined by simple clustering methods.”
Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition (2018, methodology): “Speech dereverberation can be achieved by a typical mapping approach [12], in which a regression DNN (shown in Figure 1a) is trained by pairs of reverberant and clean LPS spectra and a linear activation function at the output of DNN is adopted instead of a nonlinear one.”
Raw waveform-based speech enhancement by fully convolutional networks (2017, background): “Because the properties in the log domain are more consistent with the human auditory system, conventionally, the log power spectrum is extracted from a raw speech signal for deep-learning-based denoising models [12, 13, 33-35].”
Interactive Speech and Noise Modeling for Speech Enhancement (2020, background): “They typically estimate a real or complex ratio mask for each T-F bin to map noisy spectra to speech spectra (Williamson, Wang, and Wang 2015; Wang, Narayanan, and Wang 2014; Choi et al. 2019) or directly predict the speech representation (Xu et al. 2013; Tan and Wang 2018).”
A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks (2017, methodology): “The dereverberation filter is only estimated from voiced speech segments, therefore achieving a poor dereverberation performance for unvoiced speech segments.”
The Phasebook: Building Complex Masks via Discrete Representations for Source Separation (2019, background): “The field of speech separation and speech enhancement has witnessed dramatic improvements in performance with the recent advent of deep learning-based techniques [1–11].”
On Training Targets for Supervised Speech Separation (2014, background): “Discussions and conclusions are provided in Section VI.”
SNR-Aware Convolutional Neural Network Modeling for Speech Enhancement (2016, methodology): “In [7, 11], a deep neural network (DNN)-based SE approach was demonstrated to be better than traditional SE models.”
Multichannel Audio Source Separation With Deep Neural Networks (2016, methodology): “usage of DNN to obtain clean spectra from noisy spectra is similar to the usage of DNNs in the context of single-channel speech enhancement in [33], [34].”