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

ICASSP 2019

ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The 2019 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

Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM


In this work we consider the one-dimensional (1D) inverse scattering problem of super-resolving the location of discrete point scatters satisfying the 1D Helmholtz equation. This inverse problem has important applications in the detection of shunt faults in electrical transmission lines and leaks in water pipelines where usually only low frequency spectral information is available from measurements. We formulate the inverse scattering problem as a sparse reconstruction problem and apply convex optimization to super-resolve the location of point scatters.

Paper Details

Authors:
Wenjie Wang, Yue Li, Zhao Li, Ross Murch
Submitted On:
6 May 2019 - 10:31pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

wwangbk_ICASSP_SP_poster.pdf

(40)

Keywords

Additional Categories

Subscribe

[1] Wenjie Wang, Yue Li, Zhao Li, Ross Murch, "Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3918. Accessed: Jan. 19, 2020.
@article{3918-19,
url = {http://sigport.org/3918},
author = {Wenjie Wang; Yue Li; Zhao Li; Ross Murch },
publisher = {IEEE SigPort},
title = {Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM},
year = {2019} }
TY - EJOUR
T1 - Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM
AU - Wenjie Wang; Yue Li; Zhao Li; Ross Murch
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3918
ER -
Wenjie Wang, Yue Li, Zhao Li, Ross Murch. (2019). Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM. IEEE SigPort. http://sigport.org/3918
Wenjie Wang, Yue Li, Zhao Li, Ross Murch, 2019. Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM. Available at: http://sigport.org/3918.
Wenjie Wang, Yue Li, Zhao Li, Ross Murch. (2019). "Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM." Web.
1. Wenjie Wang, Yue Li, Zhao Li, Ross Murch. Poster for SUPER-RESOLUTION RESULTS FOR A 1D INVERSE SCATTERING PROBLEM [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3918

Structural Recurrent Neural Network for Traffic Speed Prediction


Deep neural networks have recently demonstrated the traffic prediction capability with the time series data obtained
by sensors mounted on road segments. However, capturing spatio-temporal features of the traffic data often requires a
significant number of parameters to train, increasing computational burden. In this work we demonstrate that embedding

Paper Details

Authors:
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova
Submitted On:
6 May 2019 - 6:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2019_poster.pdf

(47)

Subscribe

[1] Youngjoo Kim, Peng Wang, Lyudmila Mihaylova, "Structural Recurrent Neural Network for Traffic Speed Prediction", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3917. Accessed: Jan. 19, 2020.
@article{3917-19,
url = {http://sigport.org/3917},
author = {Youngjoo Kim; Peng Wang; Lyudmila Mihaylova },
publisher = {IEEE SigPort},
title = {Structural Recurrent Neural Network for Traffic Speed Prediction},
year = {2019} }
TY - EJOUR
T1 - Structural Recurrent Neural Network for Traffic Speed Prediction
AU - Youngjoo Kim; Peng Wang; Lyudmila Mihaylova
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3917
ER -
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova. (2019). Structural Recurrent Neural Network for Traffic Speed Prediction. IEEE SigPort. http://sigport.org/3917
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova, 2019. Structural Recurrent Neural Network for Traffic Speed Prediction. Available at: http://sigport.org/3917.
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova. (2019). "Structural Recurrent Neural Network for Traffic Speed Prediction." Web.
1. Youngjoo Kim, Peng Wang, Lyudmila Mihaylova. Structural Recurrent Neural Network for Traffic Speed Prediction [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3917

Structural Recurrent Neural Network for Traffic Speed Prediction


Deep neural networks have recently demonstrated the traffic prediction capability with the time series data obtained by sensors mounted on road segments. However, capturing spatio-temporal features of the traffic data often requires a significant number of parameters to train, increasing computational burden. In this work we demonstrate that embedding topological information of the road network improves the process of learning traffic features.

Paper Details

Authors:
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova
Submitted On:
6 May 2019 - 6:41pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2019_poster.pdf

(43)

Subscribe

[1] Youngjoo Kim, Peng Wang, Lyudmila Mihaylova, "Structural Recurrent Neural Network for Traffic Speed Prediction", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3916. Accessed: Jan. 19, 2020.
@article{3916-19,
url = {http://sigport.org/3916},
author = {Youngjoo Kim; Peng Wang; Lyudmila Mihaylova },
publisher = {IEEE SigPort},
title = {Structural Recurrent Neural Network for Traffic Speed Prediction},
year = {2019} }
TY - EJOUR
T1 - Structural Recurrent Neural Network for Traffic Speed Prediction
AU - Youngjoo Kim; Peng Wang; Lyudmila Mihaylova
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3916
ER -
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova. (2019). Structural Recurrent Neural Network for Traffic Speed Prediction. IEEE SigPort. http://sigport.org/3916
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova, 2019. Structural Recurrent Neural Network for Traffic Speed Prediction. Available at: http://sigport.org/3916.
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova. (2019). "Structural Recurrent Neural Network for Traffic Speed Prediction." Web.
1. Youngjoo Kim, Peng Wang, Lyudmila Mihaylova. Structural Recurrent Neural Network for Traffic Speed Prediction [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3916

Time-frequency-masking-based determined BSS with application to Sparse IVA


Most of the determined blind source separation (BSS) algorithms related to the independent component analysis (ICA) were derived from mathematical models of source signals. However, such derivation restricts the application of algorithms to explicitly definable source models, i.e., an implicit model associated with some signal-processing procedure cannot be utilized within such framework.

Paper Details

Authors:
Kohei Yatabe, Daichi Kitamura
Submitted On:
6 May 2019 - 6:32am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

yatabeICASSPposter.pdf

(68)

Subscribe

[1] Kohei Yatabe, Daichi Kitamura, "Time-frequency-masking-based determined BSS with application to Sparse IVA", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3914. Accessed: Jan. 19, 2020.
@article{3914-19,
url = {http://sigport.org/3914},
author = {Kohei Yatabe; Daichi Kitamura },
publisher = {IEEE SigPort},
title = {Time-frequency-masking-based determined BSS with application to Sparse IVA},
year = {2019} }
TY - EJOUR
T1 - Time-frequency-masking-based determined BSS with application to Sparse IVA
AU - Kohei Yatabe; Daichi Kitamura
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3914
ER -
Kohei Yatabe, Daichi Kitamura. (2019). Time-frequency-masking-based determined BSS with application to Sparse IVA. IEEE SigPort. http://sigport.org/3914
Kohei Yatabe, Daichi Kitamura, 2019. Time-frequency-masking-based determined BSS with application to Sparse IVA. Available at: http://sigport.org/3914.
Kohei Yatabe, Daichi Kitamura. (2019). "Time-frequency-masking-based determined BSS with application to Sparse IVA." Web.
1. Kohei Yatabe, Daichi Kitamura. Time-frequency-masking-based determined BSS with application to Sparse IVA [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3914

PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION


In this paper, a phase-aware HPSS method through convex optimization was proposed. Based on two HPSS approaches (anisotropic smoothness and sinusoidal model), the proposed method assumes the smoothness of the complex-valued spectrogram of harmonic components calculated by iPC-STFT in the time direction. On the other hand, the time-frame-wise sparsity of percussive spectrograms was considered as a phase insensitive prior. Furthermore, the proposed method considers the perfect reconstruction constraint in the time domain instead of power spectrograms.

Paper Details

Authors:
Submitted On:
6 May 2019 - 6:02am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_hpss_ver0.4.pdf

(69)

Subscribe

[1] , "PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3913. Accessed: Jan. 19, 2020.
@article{3913-19,
url = {http://sigport.org/3913},
author = { },
publisher = {IEEE SigPort},
title = {PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION},
year = {2019} }
TY - EJOUR
T1 - PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3913
ER -
. (2019). PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION. IEEE SigPort. http://sigport.org/3913
, 2019. PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION. Available at: http://sigport.org/3913.
. (2019). "PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION." Web.
1. . PHASE-AWARE HARMONIC/PERCUSSIVE SOURCE SEPARATION VIA CONVEX OPTIMIZATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3913

LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING


Low-rankness of amplitude spectrograms has been effectively utilized in audio signal processing methods including non-negative matrix factorization. However, such methods have a fundamental limitation owing to their amplitude-only treatment where the phase of the observed signal is utilized for resynthesizing the estimated signal. In order to address this limitation, we directly treat a complex-valued spectrogram and show a complex-valued spectrogram of a sum of sinusoids can be approximately low-rank by modifying its phase.

Paper Details

Authors:
Submitted On:
6 May 2019 - 5:58am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_ipclr_ver0.4.pdf

(57)

Subscribe

[1] , "LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3912. Accessed: Jan. 19, 2020.
@article{3912-19,
url = {http://sigport.org/3912},
author = { },
publisher = {IEEE SigPort},
title = {LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING},
year = {2019} }
TY - EJOUR
T1 - LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3912
ER -
. (2019). LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING. IEEE SigPort. http://sigport.org/3912
, 2019. LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING. Available at: http://sigport.org/3912.
. (2019). "LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING." Web.
1. . LOW-RANKNESS OF COMPLEX-VALUED SPECTROGRAM AND ITS APPLICATION TO PHASE-AWARE AUDIO PROCESSING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3912

OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA


360 camera has recently become popular since it can capture the whole 360 scene. A large number of related applications have been springing up. In this paper, We propose a deep learning based object detector that can be applied directly on 360 images. The proposed detector is based on modifications of the faster RCNN model. Three modification schemes are proposed here, including (1) distortion data augmentation, (2) introducing muilti-kernel layers for improving accuracy for distorted object detection, and (3) adding position information into the model for learning spatial information.

Paper Details

Authors:
Kuan-Hsun Wang, Shang-Hong Lai
Submitted On:
6 May 2019 - 2:43am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster

(57)

Subscribe

[1] Kuan-Hsun Wang, Shang-Hong Lai, "OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3909. Accessed: Jan. 19, 2020.
@article{3909-19,
url = {http://sigport.org/3909},
author = {Kuan-Hsun Wang; Shang-Hong Lai },
publisher = {IEEE SigPort},
title = {OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA},
year = {2019} }
TY - EJOUR
T1 - OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA
AU - Kuan-Hsun Wang; Shang-Hong Lai
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3909
ER -
Kuan-Hsun Wang, Shang-Hong Lai. (2019). OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA. IEEE SigPort. http://sigport.org/3909
Kuan-Hsun Wang, Shang-Hong Lai, 2019. OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA. Available at: http://sigport.org/3909.
Kuan-Hsun Wang, Shang-Hong Lai. (2019). "OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA." Web.
1. Kuan-Hsun Wang, Shang-Hong Lai. OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3909

Low-latency deep clustering for speech separation


This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of long-short-term-memory (LSTM) networks instead of their bidirectional variant used in the original work, b) using a short synthesis window (here 8 ms) required for low-latency operation, and, c) using a buffer in the beginning of audio mixture to estimate cluster centres corresponding to constituent speakers which are then utilized to separate speakers within the rest of the signal.

Paper Details

Authors:
Shanshan Wang, Gaurav Naithani, Tuomas Virtanen
Submitted On:
7 May 2019 - 1:32pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_presentation_updated.pdf

(47)

Subscribe

[1] Shanshan Wang, Gaurav Naithani, Tuomas Virtanen, "Low-latency deep clustering for speech separation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3908. Accessed: Jan. 19, 2020.
@article{3908-19,
url = {http://sigport.org/3908},
author = {Shanshan Wang; Gaurav Naithani; Tuomas Virtanen },
publisher = {IEEE SigPort},
title = {Low-latency deep clustering for speech separation},
year = {2019} }
TY - EJOUR
T1 - Low-latency deep clustering for speech separation
AU - Shanshan Wang; Gaurav Naithani; Tuomas Virtanen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3908
ER -
Shanshan Wang, Gaurav Naithani, Tuomas Virtanen. (2019). Low-latency deep clustering for speech separation. IEEE SigPort. http://sigport.org/3908
Shanshan Wang, Gaurav Naithani, Tuomas Virtanen, 2019. Low-latency deep clustering for speech separation. Available at: http://sigport.org/3908.
Shanshan Wang, Gaurav Naithani, Tuomas Virtanen. (2019). "Low-latency deep clustering for speech separation." Web.
1. Shanshan Wang, Gaurav Naithani, Tuomas Virtanen. Low-latency deep clustering for speech separation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3908

Representation learning using convolution neural network for acoustic-to-articulatory inversion

Paper Details

Authors:
Aravind Illa, Prasanta Kumar Ghosh
Submitted On:
4 May 2019 - 8:15am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

E2E_AAI_ICASSP_19.pdf

(57)

Subscribe

[1] Aravind Illa, Prasanta Kumar Ghosh, "Representation learning using convolution neural network for acoustic-to-articulatory inversion", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3907. Accessed: Jan. 19, 2020.
@article{3907-19,
url = {http://sigport.org/3907},
author = {Aravind Illa; Prasanta Kumar Ghosh },
publisher = {IEEE SigPort},
title = {Representation learning using convolution neural network for acoustic-to-articulatory inversion},
year = {2019} }
TY - EJOUR
T1 - Representation learning using convolution neural network for acoustic-to-articulatory inversion
AU - Aravind Illa; Prasanta Kumar Ghosh
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3907
ER -
Aravind Illa, Prasanta Kumar Ghosh. (2019). Representation learning using convolution neural network for acoustic-to-articulatory inversion. IEEE SigPort. http://sigport.org/3907
Aravind Illa, Prasanta Kumar Ghosh, 2019. Representation learning using convolution neural network for acoustic-to-articulatory inversion. Available at: http://sigport.org/3907.
Aravind Illa, Prasanta Kumar Ghosh. (2019). "Representation learning using convolution neural network for acoustic-to-articulatory inversion." Web.
1. Aravind Illa, Prasanta Kumar Ghosh. Representation learning using convolution neural network for acoustic-to-articulatory inversion [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3907

A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks

Paper Details

Authors:
Haonan Wang, Wenjian Liu, Tianyi Xu, Jun Lin, Zhongfeng Wang
Submitted On:
4 May 2019 - 1:19am
Short Link:
Type:
Event:
Paper Code:

Document Files

poster

(199)

Subscribe

[1] Haonan Wang, Wenjian Liu, Tianyi Xu, Jun Lin, Zhongfeng Wang, "A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3906. Accessed: Jan. 19, 2020.
@article{3906-19,
url = {http://sigport.org/3906},
author = {Haonan Wang; Wenjian Liu; Tianyi Xu; Jun Lin; Zhongfeng Wang },
publisher = {IEEE SigPort},
title = {A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks},
year = {2019} }
TY - EJOUR
T1 - A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks
AU - Haonan Wang; Wenjian Liu; Tianyi Xu; Jun Lin; Zhongfeng Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3906
ER -
Haonan Wang, Wenjian Liu, Tianyi Xu, Jun Lin, Zhongfeng Wang. (2019). A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks. IEEE SigPort. http://sigport.org/3906
Haonan Wang, Wenjian Liu, Tianyi Xu, Jun Lin, Zhongfeng Wang, 2019. A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks. Available at: http://sigport.org/3906.
Haonan Wang, Wenjian Liu, Tianyi Xu, Jun Lin, Zhongfeng Wang. (2019). "A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks." Web.
1. Haonan Wang, Wenjian Liu, Tianyi Xu, Jun Lin, Zhongfeng Wang. A Low-latency Sparse-winograd Accelerator for Convolutional Neural Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3906

Pages