A Supervised Learning Approach to Monaural Segregation of Reverberant Speech

By Zhaozhang Jin, Deliang Wang. 2009

116 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computational Mechanics, 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 Signal Processing

Citations in the corpus

Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, neutral): “It should also be noted that inverse filtering is fundamentally sensitive to RIRs, which strongly limits the robustness of this approach [20], [32].”
Learning Spectral Mapping for Speech Dereverberation and Denoising (2015, methodology): “Wang photograph and biography not available at the time of publication.”
The Conversation: Deep Audio-Visual Speech Enhancement (2018, unknown): “by using voice characteristics of a known speaker [3, 4, 5, 6, 7].”
Exploring Monaural Features for Classification-Based Speech Segregation (2013, methodology): “In [14], [20], the pitch-based features are used in training a classifier to separate target and interference dominant units.”
On Training Targets for Supervised Speech Separation (2014, background): “In many previous studies (e.g. [10], [16], [17]), the training target (or the learning signal) is set to the ideal binary mask (IBM), which is a binary mask constructed from premixed speech and noise signals (see Section III-A for de ﬁ nition).”
A Deep Ensemble Learning Method for Monaural Speech Separation (2016, methodology): “Jin and Wang [19] employed multilayer perceptron with one hidden layer, to estimate the IBM, and their method demonstrates promising results in reverberant conditions.”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “A related, earlier 518 target aims for the maximal SNR in the context of IBM esti- 519 mation [91].”
Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks (2014, background): “…in classi ﬁ cation-based segregation including kernel density estimation [28] and histograms [13] in the binaural domain, and Gaussian mixture models (GMM) [32], [20], support vector machines (SVM)[12], multilayer per-ceptrons (MLP) [19], and deep neural networks (DNNs) [40] in the monaural domain.”