Sorry, you need to enable JavaScript to visit this website.

Source separation (MLR-SSEP)

Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis

Sai Kumar Popuri
Zois Boukouvalas

Paper Details

Authors:
Sai Kumar Popuri
Zois Boukouvalas
Sai K. Popuri, Zois Boukouvalas
Submitted On:
25 October 2019 - 4:30pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

MLSP_2019.pdf

(11)

Keywords

Subscribe

Send Author a Private Message
[1] Sai K. Popuri, Zois Boukouvalas, "Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4896. Accessed: Nov. 21, 2019.
@article{4896-19,
url = {http://sigport.org/4896},
author = {Sai K. Popuri; Zois Boukouvalas },
publisher = {IEEE SigPort},
title = {Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis},
year = {2019} }
TY - EJOUR
T1 - Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis
AU - Sai K. Popuri; Zois Boukouvalas
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4896
ER -
Sai K. Popuri, Zois Boukouvalas. (2019). Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis. IEEE SigPort. http://sigport.org/4896
Sai K. Popuri, Zois Boukouvalas, 2019. Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis. Available at: http://sigport.org/4896.
Sai K. Popuri, Zois Boukouvalas. (2019). "Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis." Web.
1. Sai K. Popuri, Zois Boukouvalas. Efficient Parameter Estimation for Semi-Continuous Data: An Application to Independent Component Analysis [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4896

HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?

Debadatta Dash

Functional connectivity analysis by detecting neuronal coactivation in the brain can be efficiently done using Resting State Functional Magnetic Resonance Imaging (rs-fMRI) analysis. Most of the existing research in this area employ correlation-based group averaging strategies of spatial smoothing and temporal normalization of fMRI scans, whose reliability of results heavily depends on the voxel resolution of fMRI scan as well as scanning duration. Scanning period from 5 to 11 minutes has been chosen by most of the studies while estimating the connectivity of brain networks.

Paper Details

Authors:
Debadatta Dash
Debadatta Dash, Anil Kumar Sao, Jun Wang, Bharat Biswal
Submitted On:
22 November 2018 - 2:29pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Dash_oral_GlobalSIP_fMRI.pdf

(92)

Keywords

Additional Categories

Subscribe

Send Author a Private Message
[1] Debadatta Dash, Anil Kumar Sao, Jun Wang, Bharat Biswal, "HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3720. Accessed: Nov. 21, 2019.
@article{3720-18,
url = {http://sigport.org/3720},
author = {Debadatta Dash; Anil Kumar Sao; Jun Wang; Bharat Biswal },
publisher = {IEEE SigPort},
title = {HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?},
year = {2018} }
TY - EJOUR
T1 - HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?
AU - Debadatta Dash; Anil Kumar Sao; Jun Wang; Bharat Biswal
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3720
ER -
Debadatta Dash, Anil Kumar Sao, Jun Wang, Bharat Biswal. (2018). HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?. IEEE SigPort. http://sigport.org/3720
Debadatta Dash, Anil Kumar Sao, Jun Wang, Bharat Biswal, 2018. HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?. Available at: http://sigport.org/3720.
Debadatta Dash, Anil Kumar Sao, Jun Wang, Bharat Biswal. (2018). "HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS?." Web.
1. Debadatta Dash, Anil Kumar Sao, Jun Wang, Bharat Biswal. HOW MANY FMRI SCANS ARE NECESSARY AND SUFFICIENT FOR RESTING BRAIN CONNECTIVITY ANALYSIS? [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3720

Deep attractor networks for speaker re-identification and blind source separation

Lukas Drude

Deep Clustering (DC) and Deep Attractor Networks (DANs) are a data-driven way to monaural blind source separation.
Both approaches provide astonishing single channel performance but have not yet been generalized to block-online processing.
When separating speech in a continuous stream with a block-online algorithm, it needs to be determined in each block which of the output streams belongs to whom.
In this contribution we solve this block permutation problem by introducing an additional speaker identification embedding to the DAN model structure.

Paper Details

Authors:
Lukas Drude
Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach
Submitted On:
19 April 2018 - 7:00pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2018-04-17_drude.pdf

(188)

Keywords

Subscribe

Send Author a Private Message
[1] Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach, "Deep attractor networks for speaker re-identification and blind source separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3037. Accessed: Nov. 21, 2019.
@article{3037-18,
url = {http://sigport.org/3037},
author = {Lukas Drude; Thilo von Neumann; Reinhold Haeb-Umbach },
publisher = {IEEE SigPort},
title = {Deep attractor networks for speaker re-identification and blind source separation},
year = {2018} }
TY - EJOUR
T1 - Deep attractor networks for speaker re-identification and blind source separation
AU - Lukas Drude; Thilo von Neumann; Reinhold Haeb-Umbach
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3037
ER -
Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach. (2018). Deep attractor networks for speaker re-identification and blind source separation. IEEE SigPort. http://sigport.org/3037
Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach, 2018. Deep attractor networks for speaker re-identification and blind source separation. Available at: http://sigport.org/3037.
Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach. (2018). "Deep attractor networks for speaker re-identification and blind source separation." Web.
1. Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach. Deep attractor networks for speaker re-identification and blind source separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3037

TasNet: time-domain audio separation network for real-time, single-channel speech separation

Yi Luo

Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short latency applications. Most methods attempt to construct a mask for each source in time-frequency representation of the mixture signal which is not necessarily an optimal representation for speech separation.

Paper Details

Authors:
Yi Luo
Yi Luo, Nima Mesgarani
Submitted On:
19 April 2018 - 2:11pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018-poster.pdf

(262)

Keywords

Subscribe

Send Author a Private Message
[1] Yi Luo, Nima Mesgarani, "TasNet: time-domain audio separation network for real-time, single-channel speech separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2987. Accessed: Nov. 21, 2019.
@article{2987-18,
url = {http://sigport.org/2987},
author = {Yi Luo; Nima Mesgarani },
publisher = {IEEE SigPort},
title = {TasNet: time-domain audio separation network for real-time, single-channel speech separation},
year = {2018} }
TY - EJOUR
T1 - TasNet: time-domain audio separation network for real-time, single-channel speech separation
AU - Yi Luo; Nima Mesgarani
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2987
ER -
Yi Luo, Nima Mesgarani. (2018). TasNet: time-domain audio separation network for real-time, single-channel speech separation. IEEE SigPort. http://sigport.org/2987
Yi Luo, Nima Mesgarani, 2018. TasNet: time-domain audio separation network for real-time, single-channel speech separation. Available at: http://sigport.org/2987.
Yi Luo, Nima Mesgarani. (2018). "TasNet: time-domain audio separation network for real-time, single-channel speech separation." Web.
1. Yi Luo, Nima Mesgarani. TasNet: time-domain audio separation network for real-time, single-channel speech separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2987

Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction

Daniel Stoller

The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data augmentation is used to combat overfitting. Mixing random tracks, however, can even reduce separation performance as instruments in real music are strongly correlated. The key concept in our approach is that source estimates of an optimal separator should be indistinguishable from real source signals.

Paper Details

Authors:
Daniel Stoller
Daniel Stoller, Sebastian Ewert, Simon Dixon
Submitted On:
18 April 2018 - 3:25pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation slides version 3

(174)

Presentation slides final version

(407)

Keywords

Subscribe

Send Author a Private Message
[1] Daniel Stoller, Sebastian Ewert, Simon Dixon, "Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2901. Accessed: Nov. 21, 2019.
@article{2901-18,
url = {http://sigport.org/2901},
author = {Daniel Stoller; Sebastian Ewert; Simon Dixon },
publisher = {IEEE SigPort},
title = {Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction},
year = {2018} }
TY - EJOUR
T1 - Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction
AU - Daniel Stoller; Sebastian Ewert; Simon Dixon
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2901
ER -
Daniel Stoller, Sebastian Ewert, Simon Dixon. (2018). Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction. IEEE SigPort. http://sigport.org/2901
Daniel Stoller, Sebastian Ewert, Simon Dixon, 2018. Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction. Available at: http://sigport.org/2901.
Daniel Stoller, Sebastian Ewert, Simon Dixon. (2018). "Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction." Web.
1. Daniel Stoller, Sebastian Ewert, Simon Dixon. Semi-Supervised Adversarial Audio Source Separation applied to Singing Voice Extraction [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2901

SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES

Alper Erdogan

In this article, we propose a Bounded Component Analysis (BCA) approach for the separation of the convolutive mixtures of sparse sources. The corresponding algorithm is derived from a geometric objective function defined over a completely deterministic setting. Therefore, it is applicable to sources which can be independent or dependent in both space and time dimensions. We show that all global optima of the proposed objective are perfect separators. We also provide numerical examples to illustrate the performance of the algorithm.

Paper Details

Authors:
Alper Erdogan
Eren Babatas
Submitted On:
12 April 2018 - 12:32pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

posterconvolutivesparsebca.pdf

(196)

Keywords

Subscribe

Send Author a Private Message
[1] Eren Babatas, "SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2433. Accessed: Nov. 21, 2019.
@article{2433-18,
url = {http://sigport.org/2433},
author = {Eren Babatas },
publisher = {IEEE SigPort},
title = {SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES},
year = {2018} }
TY - EJOUR
T1 - SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES
AU - Eren Babatas
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2433
ER -
Eren Babatas. (2018). SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES. IEEE SigPort. http://sigport.org/2433
Eren Babatas, 2018. SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES. Available at: http://sigport.org/2433.
Eren Babatas. (2018). "SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES." Web.
1. Eren Babatas. SPARSE BOUNDED COMPONENT ANALYSIS FOR CONVOLUTIVE MIXTURES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2433

A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference

Glenn G. Ko

Paper Details

Authors:
Glenn G. Ko
Rob A. Rutenbar
Submitted On:
7 March 2017 - 12:55pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ko-icassp2017-poster.pdf

(349)

Keywords

Subscribe

Send Author a Private Message
[1] Rob A. Rutenbar, "A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1652. Accessed: Nov. 21, 2019.
@article{1652-17,
url = {http://sigport.org/1652},
author = {Rob A. Rutenbar },
publisher = {IEEE SigPort},
title = {A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference},
year = {2017} }
TY - EJOUR
T1 - A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference
AU - Rob A. Rutenbar
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1652
ER -
Rob A. Rutenbar. (2017). A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference. IEEE SigPort. http://sigport.org/1652
Rob A. Rutenbar, 2017. A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference. Available at: http://sigport.org/1652.
Rob A. Rutenbar. (2017). "A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference." Web.
1. Rob A. Rutenbar. A Case Study of Machine Learning Hardware: Real-Time Source Separation using Markov Random Fields via Sampling-based Inference [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1652

Learning complex-valued latent filters with absolute cosine similarity

Anh Nguyen

Paper Details

Authors:
Anh Nguyen
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon
Submitted On:
5 March 2017 - 6:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2017_slides.pdf

(265)

Keywords

Subscribe

Send Author a Private Message
[1] Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon, "Learning complex-valued latent filters with absolute cosine similarity", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1641. Accessed: Nov. 21, 2019.
@article{1641-17,
url = {http://sigport.org/1641},
author = {Anh H.T. Nguyen; V.G. Reju; Andy W.H. Khong; and Ing Yann Soon },
publisher = {IEEE SigPort},
title = {Learning complex-valued latent filters with absolute cosine similarity},
year = {2017} }
TY - EJOUR
T1 - Learning complex-valued latent filters with absolute cosine similarity
AU - Anh H.T. Nguyen; V.G. Reju; Andy W.H. Khong; and Ing Yann Soon
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1641
ER -
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon. (2017). Learning complex-valued latent filters with absolute cosine similarity. IEEE SigPort. http://sigport.org/1641
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon, 2017. Learning complex-valued latent filters with absolute cosine similarity. Available at: http://sigport.org/1641.
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon. (2017). "Learning complex-valued latent filters with absolute cosine similarity." Web.
1. Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon. Learning complex-valued latent filters with absolute cosine similarity [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1641

Learning complex-valued latent filters with absolute cosine similarity

Anh Nguyen

We propose a new sparse coding technique based on the power mean of phase-invariant cosine distances. Our approach is a generalization of sparse filtering and K-hyperlines clustering. It offers a better sparsity enforcer than the L1/L2 norm ratio that is typically used in sparse filtering. At the same time, the proposed approach scales better than the clustering counter parts for high-dimensional input. Our algorithm fully exploits the prior information obtained by preprocessing the observed data with whitening via an efficient row-wise decoupling scheme.

Paper Details

Authors:
Anh Nguyen
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon
Submitted On:
5 March 2017 - 6:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

AnhHTNguyen_icassp2017_poster.pdf

(306)

Keywords

Subscribe

Send Author a Private Message
[1] Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon, "Learning complex-valued latent filters with absolute cosine similarity", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1640. Accessed: Nov. 21, 2019.
@article{1640-17,
url = {http://sigport.org/1640},
author = {Anh H.T. Nguyen; V.G. Reju; Andy W.H. Khong; and Ing Yann Soon },
publisher = {IEEE SigPort},
title = {Learning complex-valued latent filters with absolute cosine similarity},
year = {2017} }
TY - EJOUR
T1 - Learning complex-valued latent filters with absolute cosine similarity
AU - Anh H.T. Nguyen; V.G. Reju; Andy W.H. Khong; and Ing Yann Soon
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1640
ER -
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon. (2017). Learning complex-valued latent filters with absolute cosine similarity. IEEE SigPort. http://sigport.org/1640
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon, 2017. Learning complex-valued latent filters with absolute cosine similarity. Available at: http://sigport.org/1640.
Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon. (2017). "Learning complex-valued latent filters with absolute cosine similarity." Web.
1. Anh H.T. Nguyen, V.G. Reju, Andy W.H. Khong, and Ing Yann Soon. Learning complex-valued latent filters with absolute cosine similarity [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1640

LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS

Gaurav Naithani
Giambattista Parascandolo

Sound source separation at low-latency requires that each in- coming frame of audio data be processed at very low de- lay, and outputted as soon as possible. For practical pur- poses involving human listeners, a 20 ms algorithmic delay is the uppermost limit which is comfortable to the listener. In this paper, we propose a low-latency (algorithmic delay ≤ 20 ms) deep neural network (DNN) based source sepa- ration method.

Paper Details

Authors:
Gaurav Naithani
Giambattista Parascandolo
Tom Barker, Niels Henrik Pontoppidan, Tuomas Virtanen
Submitted On:
8 December 2016 - 3:27pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

GlobalSIP_poster2.pdf

(449)

Keywords

Subscribe

Send Author a Private Message
[1] Tom Barker, Niels Henrik Pontoppidan, Tuomas Virtanen, "LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1426. Accessed: Nov. 21, 2019.
@article{1426-16,
url = {http://sigport.org/1426},
author = {Tom Barker; Niels Henrik Pontoppidan; Tuomas Virtanen },
publisher = {IEEE SigPort},
title = {LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS},
year = {2016} }
TY - EJOUR
T1 - LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS
AU - Tom Barker; Niels Henrik Pontoppidan; Tuomas Virtanen
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1426
ER -
Tom Barker, Niels Henrik Pontoppidan, Tuomas Virtanen. (2016). LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS. IEEE SigPort. http://sigport.org/1426
Tom Barker, Niels Henrik Pontoppidan, Tuomas Virtanen, 2016. LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS. Available at: http://sigport.org/1426.
Tom Barker, Niels Henrik Pontoppidan, Tuomas Virtanen. (2016). "LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS." Web.
1. Tom Barker, Niels Henrik Pontoppidan, Tuomas Virtanen. LOW-LATENCY SOUND SOURCE SEPARATION USING DEEP NEURAL NETWORKS [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1426

Pages