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

Machine Learning for Signal Processing

FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION


Examples of subband filters learned using ConvRBM: (a) filters in time-domain (i.e., impulse responses), (b) filters in frequency-domain (i.e., frequency responses).

Convolutional Restricted Boltzmann Machine (ConvRBM) as a model for speech signal is presented in this paper. We have
developed ConvRBM with sampling from noisy rectified linear units (NReLUs). ConvRBM is trained in an unsupervised way to model speech signal of arbitrary lengths. Weights of the model can represent an auditory-like filterbank. Our

poster.pdf

PDF icon poster.pdf (359 downloads)

Paper Details

Authors:
Hardik B. Sailor, Hemant A. Patil
Submitted On:
31 March 2016 - 4:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster.pdf

(359 downloads)

Keywords

Subscribe

[1] Hardik B. Sailor, Hemant A. Patil, "FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1075. Accessed: Sep. 20, 2017.
@article{1075-16,
url = {http://sigport.org/1075},
author = {Hardik B. Sailor; Hemant A. Patil },
publisher = {IEEE SigPort},
title = {FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION},
year = {2016} }
TY - EJOUR
T1 - FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION
AU - Hardik B. Sailor; Hemant A. Patil
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1075
ER -
Hardik B. Sailor, Hemant A. Patil. (2016). FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION. IEEE SigPort. http://sigport.org/1075
Hardik B. Sailor, Hemant A. Patil, 2016. FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION. Available at: http://sigport.org/1075.
Hardik B. Sailor, Hemant A. Patil. (2016). "FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION." Web.
1. Hardik B. Sailor, Hemant A. Patil. FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1075

FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION


Examples of subband filters learned using ConvRBM: (a) filters in time-domain (i.e., impulse responses), (b) filters in frequency-domain (i.e., frequency responses).

Convolutional Restricted Boltzmann Machine (ConvRBM) as a model for speech signal is presented in this paper. We have
developed ConvRBM with sampling from noisy rectified linear units (NReLUs). ConvRBM is trained in an unsupervised way to model speech signal of arbitrary lengths. Weights of the model can represent an auditory-like filterbank. Our

poster.pdf

PDF icon poster.pdf (359 downloads)

Paper Details

Authors:
Hardik B. Sailor, Hemant A. Patil
Submitted On:
31 March 2016 - 4:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster.pdf

(359 downloads)

Keywords

Subscribe

[1] Hardik B. Sailor, Hemant A. Patil, "FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1074. Accessed: Sep. 20, 2017.
@article{1074-16,
url = {http://sigport.org/1074},
author = {Hardik B. Sailor; Hemant A. Patil },
publisher = {IEEE SigPort},
title = {FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION},
year = {2016} }
TY - EJOUR
T1 - FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION
AU - Hardik B. Sailor; Hemant A. Patil
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1074
ER -
Hardik B. Sailor, Hemant A. Patil. (2016). FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION. IEEE SigPort. http://sigport.org/1074
Hardik B. Sailor, Hemant A. Patil, 2016. FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION. Available at: http://sigport.org/1074.
Hardik B. Sailor, Hemant A. Patil. (2016). "FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION." Web.
1. Hardik B. Sailor, Hemant A. Patil. FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1074

Orthogonal Sparse Eigenvectors: A Procrustes Problem


The problem of estimating sparse eigenvectors of a symmetric matrix attracts a lot of attention in many applications, especially those with high dimensional data set. While classical eigenvectors can be obtained as the solution of a maximization

SPCAposter.pdf

PDF icon SPCAposter.pdf (227 downloads)

Paper Details

Authors:
Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar
Submitted On:
22 March 2016 - 2:22am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SPCAposter.pdf

(227 downloads)

Keywords

Subscribe

[1] Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar, "Orthogonal Sparse Eigenvectors: A Procrustes Problem", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/954. Accessed: Sep. 20, 2017.
@article{954-16,
url = {http://sigport.org/954},
author = {Konstantinos Benidis; Ying Sun; Prabhu Babu; Daniel P. Palomar },
publisher = {IEEE SigPort},
title = {Orthogonal Sparse Eigenvectors: A Procrustes Problem},
year = {2016} }
TY - EJOUR
T1 - Orthogonal Sparse Eigenvectors: A Procrustes Problem
AU - Konstantinos Benidis; Ying Sun; Prabhu Babu; Daniel P. Palomar
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/954
ER -
Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar. (2016). Orthogonal Sparse Eigenvectors: A Procrustes Problem. IEEE SigPort. http://sigport.org/954
Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar, 2016. Orthogonal Sparse Eigenvectors: A Procrustes Problem. Available at: http://sigport.org/954.
Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar. (2016). "Orthogonal Sparse Eigenvectors: A Procrustes Problem." Web.
1. Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar. Orthogonal Sparse Eigenvectors: A Procrustes Problem [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/954

Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis


Differential privacy is a strong, cryptographically-motivated definition of privacy that has recently received a significant amount of research attention for its robustness to known attacks. The principal component analysis (PCA) algorithm is frequently used in signal processing, machine learning and statistics pipelines. In this paper, we propose a new algorithm for differentially-private computation of PCA and compare the performance empirically with some recent state-of-the-art algorithms on different data sets.

Paper Details

Authors:
Hafiz Imtiaz, Anand D. Sarwate
Submitted On:
20 March 2016 - 4:43am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Imtiaz_Sarwate_ICASSP2016_ver2.pdf

(192 downloads)

Keywords

Subscribe

[1] Hafiz Imtiaz, Anand D. Sarwate, "Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/860. Accessed: Sep. 20, 2017.
@article{860-16,
url = {http://sigport.org/860},
author = {Hafiz Imtiaz; Anand D. Sarwate },
publisher = {IEEE SigPort},
title = {Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis},
year = {2016} }
TY - EJOUR
T1 - Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis
AU - Hafiz Imtiaz; Anand D. Sarwate
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/860
ER -
Hafiz Imtiaz, Anand D. Sarwate. (2016). Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis. IEEE SigPort. http://sigport.org/860
Hafiz Imtiaz, Anand D. Sarwate, 2016. Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis. Available at: http://sigport.org/860.
Hafiz Imtiaz, Anand D. Sarwate. (2016). "Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis." Web.
1. Hafiz Imtiaz, Anand D. Sarwate. Symmetric Matrix Perturbation For Differentially-Private Principal Component Analysis [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/860

Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification


Recent work on zero resource word discovery makes intensive use of audio fragment clustering to find repeating speech patterns. In the absence of acoustic models, the clustering step traditionally relies on dynamic time warping (DTW) to compare two samples and thus suffers from the known limitations of this technique. We propose a new sample comparison method, called 'similarity by terative classification', that exploits the modeling capacities of hidden Markov models (HMM) with no supervision.

Paper Details

Authors:
Amélie Royer, Guillaume Gravier, Vincent Claveau
Submitted On:
19 March 2016 - 2:37pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_ICASSP.pdf

(531 downloads)

Keywords

Subscribe

[1] Amélie Royer, Guillaume Gravier, Vincent Claveau, "Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/829. Accessed: Sep. 20, 2017.
@article{829-16,
url = {http://sigport.org/829},
author = {Amélie Royer; Guillaume Gravier; Vincent Claveau },
publisher = {IEEE SigPort},
title = {Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification},
year = {2016} }
TY - EJOUR
T1 - Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification
AU - Amélie Royer; Guillaume Gravier; Vincent Claveau
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/829
ER -
Amélie Royer, Guillaume Gravier, Vincent Claveau. (2016). Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification. IEEE SigPort. http://sigport.org/829
Amélie Royer, Guillaume Gravier, Vincent Claveau, 2016. Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification. Available at: http://sigport.org/829.
Amélie Royer, Guillaume Gravier, Vincent Claveau. (2016). "Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification." Web.
1. Amélie Royer, Guillaume Gravier, Vincent Claveau. Audio Word Similarity for Clustering with Zero Resources based on iterative HMM Classification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/829

Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics


Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics

In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes.

Paper Details

Authors:
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi
Submitted On:
16 July 2016 - 11:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

DCA_ICASSP16_Poster.pdf

(822 downloads)

Keywords

Additional Categories

Subscribe

[1] Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi, "Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/828. Accessed: Sep. 20, 2017.
@article{828-16,
url = {http://sigport.org/828},
author = {Mohammad Haghighat; Mohamed Abdel-Mottaleb; Wadee Alhalabi },
publisher = {IEEE SigPort},
title = {Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics},
year = {2016} }
TY - EJOUR
T1 - Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics
AU - Mohammad Haghighat; Mohamed Abdel-Mottaleb; Wadee Alhalabi
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/828
ER -
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi. (2016). Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics. IEEE SigPort. http://sigport.org/828
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi, 2016. Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics. Available at: http://sigport.org/828.
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi. (2016). "Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics." Web.
1. Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi. Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/828

DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING


Imaging techniques involve counting of photons striking a detector.
Due to fluctuations in the counting process, the measured
photon counts are known to be corrupted by Poisson
noise. In this paper, we propose a blind dictionary learning
framework for the reconstruction of photographic image data
from Poisson corrupted measurements acquired by a compressive
camera. We exploit the inherent non-negativity of the
data by modeling the dictionary as well as the sparse dictionary
coefficients as non-negative entities, and infer these directly

Paper Details

Authors:
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade
Submitted On:
19 March 2016 - 4:43am
Short Link:
Type:
Event:

Document Files

ICASSP_poster.pdf

(428 downloads)

Keywords

Subscribe

[1] Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade, "DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/791. Accessed: Sep. 20, 2017.
@article{791-16,
url = {http://sigport.org/791},
author = {Sukanya Patil; Rajbabu Velmurugan; Ajit Rajwade },
publisher = {IEEE SigPort},
title = {DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING},
year = {2016} }
TY - EJOUR
T1 - DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING
AU - Sukanya Patil; Rajbabu Velmurugan; Ajit Rajwade
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/791
ER -
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade. (2016). DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING. IEEE SigPort. http://sigport.org/791
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade, 2016. DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING. Available at: http://sigport.org/791.
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade. (2016). "DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING." Web.
1. Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade. DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/791

Stable and Symmetric Filter Convolutional Neural Network

Paper Details

Authors:
Raymond Yeh, Mark Hasegawa-Johnson, Minh N. Do
Submitted On:
18 March 2016 - 10:27pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp2016.pdf

(348 downloads)

Keywords

Subscribe

[1] Raymond Yeh, Mark Hasegawa-Johnson, Minh N. Do, "Stable and Symmetric Filter Convolutional Neural Network", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/781. Accessed: Sep. 20, 2017.
@article{781-16,
url = {http://sigport.org/781},
author = {Raymond Yeh; Mark Hasegawa-Johnson; Minh N. Do },
publisher = {IEEE SigPort},
title = {Stable and Symmetric Filter Convolutional Neural Network},
year = {2016} }
TY - EJOUR
T1 - Stable and Symmetric Filter Convolutional Neural Network
AU - Raymond Yeh; Mark Hasegawa-Johnson; Minh N. Do
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/781
ER -
Raymond Yeh, Mark Hasegawa-Johnson, Minh N. Do. (2016). Stable and Symmetric Filter Convolutional Neural Network. IEEE SigPort. http://sigport.org/781
Raymond Yeh, Mark Hasegawa-Johnson, Minh N. Do, 2016. Stable and Symmetric Filter Convolutional Neural Network. Available at: http://sigport.org/781.
Raymond Yeh, Mark Hasegawa-Johnson, Minh N. Do. (2016). "Stable and Symmetric Filter Convolutional Neural Network." Web.
1. Raymond Yeh, Mark Hasegawa-Johnson, Minh N. Do. Stable and Symmetric Filter Convolutional Neural Network [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/781

Deep Learning: Propelling Recent Rapid Advances in AI

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

GlobalSIP-Plenary-LiDeng-Dec16-2015 - reduced.pptx

(256 downloads)

Keywords

Subscribe

[1] , "Deep Learning: Propelling Recent Rapid Advances in AI", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/600. Accessed: Sep. 20, 2017.
@article{600-16,
url = {http://sigport.org/600},
author = { },
publisher = {IEEE SigPort},
title = {Deep Learning: Propelling Recent Rapid Advances in AI},
year = {2016} }
TY - EJOUR
T1 - Deep Learning: Propelling Recent Rapid Advances in AI
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/600
ER -
. (2016). Deep Learning: Propelling Recent Rapid Advances in AI. IEEE SigPort. http://sigport.org/600
, 2016. Deep Learning: Propelling Recent Rapid Advances in AI. Available at: http://sigport.org/600.
. (2016). "Deep Learning: Propelling Recent Rapid Advances in AI." Web.
1. . Deep Learning: Propelling Recent Rapid Advances in AI [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/600

A feasibility study of automated plug-load identification from high-frequency measurements


Plug-meters benefit many grid and building-level energy management applications like automated load control and load scheduling. However, installing and maintaining large and/orlong term deployments of such meters requires assignment and updating of the identity (labels) of electrical loads connected to them. Although the literature on electricity disaggregation and appliance identification is extensive, there is no consensus on the generalizability of the proposed solutions, especially with respect to the features that are extracted from voltage and current measurements.

Paper Details

Authors:
Emre Can Kara, Suman Giri, Mario Berges
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

A feasibility study of automated plug-load identification from high-frequency measurements.pdf

(260 downloads)

Keywords

Subscribe

[1] Emre Can Kara, Suman Giri, Mario Berges, "A feasibility study of automated plug-load identification from high-frequency measurements", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/334. Accessed: Sep. 20, 2017.
@article{334-15,
url = {http://sigport.org/334},
author = {Emre Can Kara; Suman Giri; Mario Berges },
publisher = {IEEE SigPort},
title = {A feasibility study of automated plug-load identification from high-frequency measurements},
year = {2015} }
TY - EJOUR
T1 - A feasibility study of automated plug-load identification from high-frequency measurements
AU - Emre Can Kara; Suman Giri; Mario Berges
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/334
ER -
Emre Can Kara, Suman Giri, Mario Berges. (2015). A feasibility study of automated plug-load identification from high-frequency measurements. IEEE SigPort. http://sigport.org/334
Emre Can Kara, Suman Giri, Mario Berges, 2015. A feasibility study of automated plug-load identification from high-frequency measurements. Available at: http://sigport.org/334.
Emre Can Kara, Suman Giri, Mario Berges. (2015). "A feasibility study of automated plug-load identification from high-frequency measurements." Web.
1. Emre Can Kara, Suman Giri, Mario Berges. A feasibility study of automated plug-load identification from high-frequency measurements [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/334

Pages