Model-Based Expectation-Maximization Source Separation and Localization

By Michael I. Mandel, Ron J. Weiss, D. Ellis. IEEE Transactions on Audio, Speech, and Language Processing, 2010

332 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Signal Processing

View Paper: https://www.semanticscholar.org/paper/41f1975a774606d0b501fdfcf870aadb7b028d8c

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 Signal Processing

Citations in the corpus

A General Flexible Framework for the Handling of Prior Information in Audio Source Separation (2012, background): “The benefit of local Gaussian modeling is that it naturally leads to closed form expressions in the multichannel case and allows the modeling of diffuse sources [19], contrary to the models in [33]–[40].”
Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures (2017, methodology): “This problem has been investigated using both single and multi-channel source separation techniques, including NMF [1], ICA [2] or clustering of spatial cues [3, 4, 5].”
Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation (2018, methodology): “Our method is shown to give much better separation performance in the stereo case in terms of signal-to-distortion ratio (SDR) than the oracle multi-channel Wiener ﬁlter (MCWF) [9], model-based EM source separation and localization (MESSL) [18], and GCC-NMF [19] algorithms.”
Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks (2014, methodology): “A joint localization and segregation approach [23], dubbed MESSL, uses spatial clustering for source localization.”
An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, neutral): “As an alternative to beamforming and post-filtering, multichannel source separation techniques such as model-based expectation-maximization source separation and localization (MESSL) (Mandel et al., 2010) and full-rank local Gaussian modeling (Duong et al.”
New Era for Robust Speech Recognition (2017, background): “Several approaches have attempted to alleviate this problem by applying a separate smoothing process after mask estimation [13, 19, 35, 56].”
Speech intelligibility in reverberation with ideal binary masking: effects of early reflections and signal-to-noise ratio threshold. (2013, background): “Alternatively, dereverberation and speech separation systems often treat the direct sound (anechoic) target speech as the desired signal under the assumption that both noise and reverberation degrade signal quality (e.g., Miyoshi and Kaneda, 1988; Buchner et al. , 2004; Mandel et al. , 2010).”
Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion (2016, background): “One way to overcome the problems just mentioned is to perform multiple speech-source localization [25], [26], [27] and to associate speech sources with persons.”
A Survey of Sound Source Localization with Deep Learning Methods (2021, methodology): “Methods based on probabilistic generative mixture models have been proposed in, e.g., [84], [85], [86], [87], [88], [89].”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, neutral): “In [265], a soft mask is proposed based on a mapping between the ITD values and the relative contribution of the target source.”
Underdetermined Convolutive Blind Source Separation via Frequency Bin-Wise Clustering and Permutation Alignment (2011, background): “Some improvement for highly reverberant conditions could be gained by modeling TDOA variations with a mixture of Gaussians [18] or gradually making the parameters frequency dependent [19].”