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

ICASSP 2020

ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The ICASSP 2020 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world. Visit website.

Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network


Blood pressure (BP) is a vital sign of the human body and an important parameter for early detection of cardiovascular diseases. It is usually measured using cuff-based devices or monitored invasively in critically-ill patients. This paper presents two techniques that enable continuous and noninvasive cuff-less BP estimation using photoplethysmography (PPG) signals with Convolutional Neural Networks (CNNs). The first technique is calibration-free.

Paper Details

Authors:
Oded Schlesinger, Nitai Vigderhouse, Danny Eytan, Yair Moshe
Submitted On:
13 May 2020 - 4:48pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP Presentation - Blood Pressure Estimation from PPG Signals.pdf

(47)

Subscribe

[1] Oded Schlesinger, Nitai Vigderhouse, Danny Eytan, Yair Moshe, "Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5138. Accessed: Aug. 06, 2020.
@article{5138-20,
url = {http://sigport.org/5138},
author = {Oded Schlesinger; Nitai Vigderhouse; Danny Eytan; Yair Moshe },
publisher = {IEEE SigPort},
title = {Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network},
year = {2020} }
TY - EJOUR
T1 - Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network
AU - Oded Schlesinger; Nitai Vigderhouse; Danny Eytan; Yair Moshe
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5138
ER -
Oded Schlesinger, Nitai Vigderhouse, Danny Eytan, Yair Moshe. (2020). Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network. IEEE SigPort. http://sigport.org/5138
Oded Schlesinger, Nitai Vigderhouse, Danny Eytan, Yair Moshe, 2020. Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network. Available at: http://sigport.org/5138.
Oded Schlesinger, Nitai Vigderhouse, Danny Eytan, Yair Moshe. (2020). "Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network." Web.
1. Oded Schlesinger, Nitai Vigderhouse, Danny Eytan, Yair Moshe. Blood Pressure Estimation from PPG Signals Using Convolutional Neural Networks and Siamese Network [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5138

Learning with Out of Distribution Data for Audio Classification


In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with out-of-distribution (OOD) instances: data that does not belong to any of the target classes, but is labelled as such. We show that detecting and relabelling certain OOD instances, rather than discarding them, can have a positive effect on learning.

Paper Details

Authors:
Wenwu Wang
Submitted On:
14 May 2020 - 8:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation.pdf

(61)

Subscribe

[1] Wenwu Wang, "Learning with Out of Distribution Data for Audio Classification", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5137. Accessed: Aug. 06, 2020.
@article{5137-20,
url = {http://sigport.org/5137},
author = {Wenwu Wang },
publisher = {IEEE SigPort},
title = {Learning with Out of Distribution Data for Audio Classification},
year = {2020} }
TY - EJOUR
T1 - Learning with Out of Distribution Data for Audio Classification
AU - Wenwu Wang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5137
ER -
Wenwu Wang. (2020). Learning with Out of Distribution Data for Audio Classification. IEEE SigPort. http://sigport.org/5137
Wenwu Wang, 2020. Learning with Out of Distribution Data for Audio Classification. Available at: http://sigport.org/5137.
Wenwu Wang. (2020). "Learning with Out of Distribution Data for Audio Classification." Web.
1. Wenwu Wang. Learning with Out of Distribution Data for Audio Classification [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5137

Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems


In this talk we present statistical signal processing methodologies on a real-world application of using Commercial Microwave Links (CMLs) as opportunistic sensors for rain monitoring. We formulate an appropriate parameter estimation problem, taking advantage on the empirically evaluated statistics of the rain, and present a new methodology for rain estimation given only the quantized minimum and maximum radio signal level measurements, which are being logged regularly by the network management systems.

Paper Details

Authors:
Submitted On:
13 May 2020 - 4:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation Slides

(20)

Keywords

Additional Categories

Subscribe

[1] , "Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5136. Accessed: Aug. 06, 2020.
@article{5136-20,
url = {http://sigport.org/5136},
author = { },
publisher = {IEEE SigPort},
title = {Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems},
year = {2020} }
TY - EJOUR
T1 - Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5136
ER -
. (2020). Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems. IEEE SigPort. http://sigport.org/5136
, 2020. Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems. Available at: http://sigport.org/5136.
. (2020). "Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems." Web.
1. . Statistical Signal Processing Approach For Rain Estimation Based on Measurements From Network Management Systems [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5136

AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT

Paper Details

Authors:
Kazuhito Koishida
Submitted On:
13 May 2020 - 4:45pm
Short Link:
Type:
Event:

Document Files

AVSE2 Presentation.pdf

(33)

Subscribe

[1] Kazuhito Koishida, "AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5135. Accessed: Aug. 06, 2020.
@article{5135-20,
url = {http://sigport.org/5135},
author = {Kazuhito Koishida },
publisher = {IEEE SigPort},
title = {AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT},
year = {2020} }
TY - EJOUR
T1 - AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT
AU - Kazuhito Koishida
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5135
ER -
Kazuhito Koishida. (2020). AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT. IEEE SigPort. http://sigport.org/5135
Kazuhito Koishida, 2020. AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT. Available at: http://sigport.org/5135.
Kazuhito Koishida. (2020). "AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT." Web.
1. Kazuhito Koishida. AV(SE)²: AUDIO-VISUAL SQUEEZE-EXCITE SPEECH ENHANCEMENT [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5135

A segmentation based deep learning framework for multimodal retinal image registration


Multimodal image registration plays an important role in diagnosing and treating ophthalmologic diseases. In this paper, a deep learning framework for multimodal retinal image registration is proposed. The framework consists of a segmentation network, feature detection and description network, and an outlier rejection network, which focuses only on the globally coarse alignment step using the perspective transformation.

Paper Details

Authors:
Yiqian Wang, Junkang Zhang, Cheolhong An, Melina Cavichini, Mahima Jhingan, Manuel J. Amador-Patarroyo, Christopher P. Long, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen
Submitted On:
13 May 2020 - 4:42pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP_slides_final.pdf

(30)

Subscribe

[1] Yiqian Wang, Junkang Zhang, Cheolhong An, Melina Cavichini, Mahima Jhingan, Manuel J. Amador-Patarroyo, Christopher P. Long, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen, "A segmentation based deep learning framework for multimodal retinal image registration", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5134. Accessed: Aug. 06, 2020.
@article{5134-20,
url = {http://sigport.org/5134},
author = {Yiqian Wang; Junkang Zhang; Cheolhong An; Melina Cavichini; Mahima Jhingan; Manuel J. Amador-Patarroyo; Christopher P. Long; Dirk-Uwe G. Bartsch; William R. Freeman; Truong Q. Nguyen },
publisher = {IEEE SigPort},
title = {A segmentation based deep learning framework for multimodal retinal image registration},
year = {2020} }
TY - EJOUR
T1 - A segmentation based deep learning framework for multimodal retinal image registration
AU - Yiqian Wang; Junkang Zhang; Cheolhong An; Melina Cavichini; Mahima Jhingan; Manuel J. Amador-Patarroyo; Christopher P. Long; Dirk-Uwe G. Bartsch; William R. Freeman; Truong Q. Nguyen
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5134
ER -
Yiqian Wang, Junkang Zhang, Cheolhong An, Melina Cavichini, Mahima Jhingan, Manuel J. Amador-Patarroyo, Christopher P. Long, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen. (2020). A segmentation based deep learning framework for multimodal retinal image registration. IEEE SigPort. http://sigport.org/5134
Yiqian Wang, Junkang Zhang, Cheolhong An, Melina Cavichini, Mahima Jhingan, Manuel J. Amador-Patarroyo, Christopher P. Long, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen, 2020. A segmentation based deep learning framework for multimodal retinal image registration. Available at: http://sigport.org/5134.
Yiqian Wang, Junkang Zhang, Cheolhong An, Melina Cavichini, Mahima Jhingan, Manuel J. Amador-Patarroyo, Christopher P. Long, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen. (2020). "A segmentation based deep learning framework for multimodal retinal image registration." Web.
1. Yiqian Wang, Junkang Zhang, Cheolhong An, Melina Cavichini, Mahima Jhingan, Manuel J. Amador-Patarroyo, Christopher P. Long, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen. A segmentation based deep learning framework for multimodal retinal image registration [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5134

BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning

Paper Details

Authors:
Dirk Slock
Submitted On:
13 May 2020 - 4:41pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP20_presentation.pdf

(22)

Subscribe

[1] Dirk Slock, "BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5133. Accessed: Aug. 06, 2020.
@article{5133-20,
url = {http://sigport.org/5133},
author = {Dirk Slock },
publisher = {IEEE SigPort},
title = {BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning},
year = {2020} }
TY - EJOUR
T1 - BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning
AU - Dirk Slock
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5133
ER -
Dirk Slock. (2020). BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning. IEEE SigPort. http://sigport.org/5133
Dirk Slock, 2020. BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning. Available at: http://sigport.org/5133.
Dirk Slock. (2020). "BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning." Web.
1. Dirk Slock. BP-VB-EP Based Static and Dynamic Sparse Bayesian Learning [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5133

Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems


Recently, a hybrid analog-digital architecture has been proposed for multiuser MIMO transmission in the millimeter-wave spectrum using reflect-arrays. The architecture exhibits scalability and high energy-efficiency while keeping the transmitter cost-efficient. Inspired by this architecture, we design a secure multiuser hybrid analog-digital precoding scheme. This scheme utilizes the method of regularized least-squares to shape the downlink beamformers, such that the signal received via malicious terminals is effectively suppressed.

Paper Details

Authors:
Saba Asaad, Rafael F. Schaefer, and H. Vincent Poor
Submitted On:
11 May 2020 - 11:25am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp20_irs_tak.pdf

(37)

Subscribe

[1] Saba Asaad, Rafael F. Schaefer, and H. Vincent Poor, "Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5131. Accessed: Aug. 06, 2020.
@article{5131-20,
url = {http://sigport.org/5131},
author = {Saba Asaad; Rafael F. Schaefer; and H. Vincent Poor },
publisher = {IEEE SigPort},
title = {Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems},
year = {2020} }
TY - EJOUR
T1 - Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems
AU - Saba Asaad; Rafael F. Schaefer; and H. Vincent Poor
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5131
ER -
Saba Asaad, Rafael F. Schaefer, and H. Vincent Poor. (2020). Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems. IEEE SigPort. http://sigport.org/5131
Saba Asaad, Rafael F. Schaefer, and H. Vincent Poor, 2020. Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems. Available at: http://sigport.org/5131.
Saba Asaad, Rafael F. Schaefer, and H. Vincent Poor. (2020). "Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems." Web.
1. Saba Asaad, Rafael F. Schaefer, and H. Vincent Poor. Hybrid Precoding for Secure Transmission in Reflect-Array-Assisted Massive MIMO Systems [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5131

Primary Path Estimator based on Individual Secondary Path for ANC Headphones

Paper Details

Authors:
Johannes Fabry, Peter Jax
Submitted On:
11 May 2020 - 3:28am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

2020_ICASSP_PPE.pdf

(29)

Subscribe

[1] Johannes Fabry, Peter Jax, "Primary Path Estimator based on Individual Secondary Path for ANC Headphones", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5130. Accessed: Aug. 06, 2020.
@article{5130-20,
url = {http://sigport.org/5130},
author = {Johannes Fabry; Peter Jax },
publisher = {IEEE SigPort},
title = {Primary Path Estimator based on Individual Secondary Path for ANC Headphones},
year = {2020} }
TY - EJOUR
T1 - Primary Path Estimator based on Individual Secondary Path for ANC Headphones
AU - Johannes Fabry; Peter Jax
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5130
ER -
Johannes Fabry, Peter Jax. (2020). Primary Path Estimator based on Individual Secondary Path for ANC Headphones. IEEE SigPort. http://sigport.org/5130
Johannes Fabry, Peter Jax, 2020. Primary Path Estimator based on Individual Secondary Path for ANC Headphones. Available at: http://sigport.org/5130.
Johannes Fabry, Peter Jax. (2020). "Primary Path Estimator based on Individual Secondary Path for ANC Headphones." Web.
1. Johannes Fabry, Peter Jax. Primary Path Estimator based on Individual Secondary Path for ANC Headphones [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5130

Revisiting Fast Spectral Clustering with Anchor Graph


In this paper, we revisit the popular affinity matrix based on the anchor graph and point out that the spectral embedding obtained using symmetric normalized Laplacian is only a side view of the bipartite structure. Based on the analysis, we propose Fast Spectral Clustering based on the Random Walk Laplacian (FRWL) method to explicitly balance the popularity of anchors and the independence of data points, which is especially important for clustering of boundary points.

Paper Details

Authors:
Submitted On:
6 May 2020 - 11:28pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

large-scale spectral clustering

(30)

Keywords

Additional Categories

Subscribe

[1] , "Revisiting Fast Spectral Clustering with Anchor Graph", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5129. Accessed: Aug. 06, 2020.
@article{5129-20,
url = {http://sigport.org/5129},
author = { },
publisher = {IEEE SigPort},
title = {Revisiting Fast Spectral Clustering with Anchor Graph},
year = {2020} }
TY - EJOUR
T1 - Revisiting Fast Spectral Clustering with Anchor Graph
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5129
ER -
. (2020). Revisiting Fast Spectral Clustering with Anchor Graph. IEEE SigPort. http://sigport.org/5129
, 2020. Revisiting Fast Spectral Clustering with Anchor Graph. Available at: http://sigport.org/5129.
. (2020). "Revisiting Fast Spectral Clustering with Anchor Graph." Web.
1. . Revisiting Fast Spectral Clustering with Anchor Graph [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5129

Transformer-based text-to-speech with weighted forced attention


This paper investigates state-of-the-art Transformer- and FastSpeech-based high-fidelity neural text-to-speech (TTS) with full-context label input for pitch accent languages. The aim is to realize faster training than conventional Tacotron-based models. Introducing phoneme durations into Tacotron-based TTS models improves both synthesis quality and stability.

Paper Details

Authors:
Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai
Submitted On:
6 May 2020 - 9:36pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2020_okamoto.pdf

(46)

Subscribe

[1] Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai, "Transformer-based text-to-speech with weighted forced attention", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5128. Accessed: Aug. 06, 2020.
@article{5128-20,
url = {http://sigport.org/5128},
author = {Takuma Okamoto; Tomoki Toda; Yoshinori Shiga; Hisashi Kawai },
publisher = {IEEE SigPort},
title = {Transformer-based text-to-speech with weighted forced attention},
year = {2020} }
TY - EJOUR
T1 - Transformer-based text-to-speech with weighted forced attention
AU - Takuma Okamoto; Tomoki Toda; Yoshinori Shiga; Hisashi Kawai
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5128
ER -
Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. (2020). Transformer-based text-to-speech with weighted forced attention. IEEE SigPort. http://sigport.org/5128
Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai, 2020. Transformer-based text-to-speech with weighted forced attention. Available at: http://sigport.org/5128.
Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. (2020). "Transformer-based text-to-speech with weighted forced attention." Web.
1. Takuma Okamoto, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. Transformer-based text-to-speech with weighted forced attention [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5128

Pages