Speech segregation based on sound localization

By Nicoleta Roman, Deliang Wang, Guy J. Brown. IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222), 2001

474 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/b23e05b17ca1e742327ce16f5ca9829e78c7a8bd

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

Ideal ratio mask estimation using deep neural networks for robust speech recognition (2013, unknown): “Supervised classification-based algorithms have been used to perform the task of IBM estimation for speech separation [13] [14].”
Exploring Monaural Features for Classification-Based Speech Segregation (2013, background): “To our knowledge, the first attempt to formulate speech segregation as a binary classification problem was made in the binaural domain [23].”
Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition (2014, methodology): “Stereo training data is also used by supervised classi ﬁ cation based speech separation algorithms [33], [36], [22], [17], [43].”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, unknown): “Following early studies in [105], [272], many recent speech enhancement and source separation approaches now rely on joint modeling and exploitation of spatial and spectral information [112], [115], [183], [228], [229], [233], [242], [273]–[275].”
On the optimality of ideal binary time-frequency masks (2008, background): “The IBM dramatically improves the intelligibility of speech corrupted by noise [5] [6] [7].”
Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks (2014, methodology): “A variety of classi ﬁ ers has been explored 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…”
Towards Scaling Up Classification-Based Speech Separation (2013, background): “It has also been shown that if the IBM is well estimated, separation algorithms can indeed improve speech intelligibility [29], [38].”
Dynamic Precedence Effect Modeling for Source Separation in Reverberant Environments (2010, methodology): “The target and interferer azimuths are obtained by warping the cross-correlograms to the azimuthal domain, reducing them to skeleton cross-correlograms [2], [14] and summing across time and frequency.”
Speech intelligibility in reverberation with ideal binary masking: effects of early reflections and signal-to-noise ratio threshold. (2013, methodology): “…to estimate the IBM from the mixture, the binary masking approach allows the use of supervised learning algorithms to perform classiﬁ-cation, which are proving to be powerful alternatives to more traditional signal enhancement methods (Roman et al. , 2003; Kim et al. , 2009; Han and Wang, 2011).”