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

ICASSP 2018

ICASSP is the world's largest and most comprehensive technical conference on signal processing and its applications. It provides a fantastic networking opportunity for like-minded professionals from around the world. ICASSP 2018 conference will feature world-class presentations by internationally renowned speakers and cutting-edge session topics. Visit ICASSP 2018.

FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING


In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model. By enforcing the model to discriminate the speakers in the training data, frame-level speaker features can be derived from the last hidden layer.

Paper Details

Authors:
Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng
Submitted On:
20 April 2018 - 7:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

180418-Full_info-LLT.pptx

(6 downloads)

Keywords

Subscribe

[1] Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng, "FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3100. Accessed: Apr. 21, 2018.
@article{3100-18,
url = {http://sigport.org/3100},
author = {Lantian Li; Zhiyuan Tang; Dong Wang; Thomas Fang Zheng },
publisher = {IEEE SigPort},
title = {FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING},
year = {2018} }
TY - EJOUR
T1 - FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING
AU - Lantian Li; Zhiyuan Tang; Dong Wang; Thomas Fang Zheng
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3100
ER -
Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng. (2018). FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING. IEEE SigPort. http://sigport.org/3100
Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng, 2018. FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING. Available at: http://sigport.org/3100.
Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng. (2018). "FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING." Web.
1. Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng. FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3100

High-speed Optical Camera Communication Using an Optimally Modulated Signal


This paper describes a high-speed optical camera communication (OCC) technique using an LED and a rolling-shutter camera. In the proposed technique, the symbols being transmitted are encoded as time delays of optimally modulated signals derived theoretically. A receiver decodes the symbols by using intensities obtained from four consecutive line sensors of a camera.

Paper Details

Authors:
Hayato Kumaki, Takayuki Akiyama, Hiromichi Hashizume
Submitted On:
20 April 2018 - 5:32am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

skah-icassp2018-poster.pdf

(4 downloads)

Keywords

Additional Categories

Subscribe

[1] Hayato Kumaki, Takayuki Akiyama, Hiromichi Hashizume, "High-speed Optical Camera Communication Using an Optimally Modulated Signal", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3099. Accessed: Apr. 21, 2018.
@article{3099-18,
url = {http://sigport.org/3099},
author = {Hayato Kumaki; Takayuki Akiyama; Hiromichi Hashizume },
publisher = {IEEE SigPort},
title = {High-speed Optical Camera Communication Using an Optimally Modulated Signal},
year = {2018} }
TY - EJOUR
T1 - High-speed Optical Camera Communication Using an Optimally Modulated Signal
AU - Hayato Kumaki; Takayuki Akiyama; Hiromichi Hashizume
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3099
ER -
Hayato Kumaki, Takayuki Akiyama, Hiromichi Hashizume. (2018). High-speed Optical Camera Communication Using an Optimally Modulated Signal. IEEE SigPort. http://sigport.org/3099
Hayato Kumaki, Takayuki Akiyama, Hiromichi Hashizume, 2018. High-speed Optical Camera Communication Using an Optimally Modulated Signal. Available at: http://sigport.org/3099.
Hayato Kumaki, Takayuki Akiyama, Hiromichi Hashizume. (2018). "High-speed Optical Camera Communication Using an Optimally Modulated Signal." Web.
1. Hayato Kumaki, Takayuki Akiyama, Hiromichi Hashizume. High-speed Optical Camera Communication Using an Optimally Modulated Signal [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3099

Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss


In this paper, we propose deep feature embedding learning for person re-identification (re-id) using lifted structured loss. Although triplet loss has been commonly used in deep neural networks for person re-id, the triplet loss-based framework is not effective in fully using the batch information. Thus, it needs to choose hard negative samples manually that is very time-consuming. To address this problem, we adopt lifted structured loss for deep neural networks that makes the network learn better feature embedding by minimizing intra-class variation and maximizing inter-class variation.

Paper Details

Authors:
Zhangping He, Zhendong Zhang, Cheolkon Jung
Submitted On:
20 April 2018 - 5:23am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2018_PersonReID_final.pdf

(6 downloads)

Keywords

Additional Categories

Subscribe

[1] Zhangping He, Zhendong Zhang, Cheolkon Jung, "Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3098. Accessed: Apr. 21, 2018.
@article{3098-18,
url = {http://sigport.org/3098},
author = {Zhangping He; Zhendong Zhang; Cheolkon Jung },
publisher = {IEEE SigPort},
title = {Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss},
year = {2018} }
TY - EJOUR
T1 - Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss
AU - Zhangping He; Zhendong Zhang; Cheolkon Jung
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3098
ER -
Zhangping He, Zhendong Zhang, Cheolkon Jung. (2018). Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss. IEEE SigPort. http://sigport.org/3098
Zhangping He, Zhendong Zhang, Cheolkon Jung, 2018. Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss. Available at: http://sigport.org/3098.
Zhangping He, Zhendong Zhang, Cheolkon Jung. (2018). "Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss." Web.
1. Zhangping He, Zhendong Zhang, Cheolkon Jung. Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3098

Determined Blind Source Separation via Proximal Splitting Algorithm


The state-of-the-art algorithms of determined blind source separation (BSS) methods based on the independent component analysis

Paper Details

Authors:
Kohei Yatabe, Daichi Kitamura
Submitted On:
20 April 2018 - 4:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2018.04.20_ICASSPポスター_PDS_ICA.pdf

(0)

Keywords

Subscribe

[1] Kohei Yatabe, Daichi Kitamura, "Determined Blind Source Separation via Proximal Splitting Algorithm", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3095. Accessed: Apr. 21, 2018.
@article{3095-18,
url = {http://sigport.org/3095},
author = {Kohei Yatabe; Daichi Kitamura },
publisher = {IEEE SigPort},
title = {Determined Blind Source Separation via Proximal Splitting Algorithm},
year = {2018} }
TY - EJOUR
T1 - Determined Blind Source Separation via Proximal Splitting Algorithm
AU - Kohei Yatabe; Daichi Kitamura
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3095
ER -
Kohei Yatabe, Daichi Kitamura. (2018). Determined Blind Source Separation via Proximal Splitting Algorithm. IEEE SigPort. http://sigport.org/3095
Kohei Yatabe, Daichi Kitamura, 2018. Determined Blind Source Separation via Proximal Splitting Algorithm. Available at: http://sigport.org/3095.
Kohei Yatabe, Daichi Kitamura. (2018). "Determined Blind Source Separation via Proximal Splitting Algorithm." Web.
1. Kohei Yatabe, Daichi Kitamura. Determined Blind Source Separation via Proximal Splitting Algorithm [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3095

EXTENDABLE NEURAL MATRIX COMPLETION

Paper Details

Authors:
Submitted On:
20 April 2018 - 4:21am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP-MC-poster.pdf

(6 downloads)

Keywords

Subscribe

[1] , "EXTENDABLE NEURAL MATRIX COMPLETION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3094. Accessed: Apr. 21, 2018.
@article{3094-18,
url = {http://sigport.org/3094},
author = { },
publisher = {IEEE SigPort},
title = {EXTENDABLE NEURAL MATRIX COMPLETION},
year = {2018} }
TY - EJOUR
T1 - EXTENDABLE NEURAL MATRIX COMPLETION
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3094
ER -
. (2018). EXTENDABLE NEURAL MATRIX COMPLETION. IEEE SigPort. http://sigport.org/3094
, 2018. EXTENDABLE NEURAL MATRIX COMPLETION. Available at: http://sigport.org/3094.
. (2018). "EXTENDABLE NEURAL MATRIX COMPLETION." Web.
1. . EXTENDABLE NEURAL MATRIX COMPLETION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3094

Phase Corrected Total Variation for Audio Signals


In optimization-based signal processing, the so-called prior term models the desired signal, and therefore its design is the key factor to achieve a good performance. For audio signals, the time-directional total variation applied to a spectrogram in combination with phase correction has been proposed recently to model sinusoidal components of the signal. Although it is a promising prior, its applicability might be restricted to some extent because of the mismatch of the assumption to the signal.

Paper Details

Authors:
Kohei Yatabe, Yasuhiro Oikawa
Submitted On:
20 April 2018 - 4:09am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2018.04.20_ICASSPポスター_iPC_TV.pdf

(0)

Keywords

Subscribe

[1] Kohei Yatabe, Yasuhiro Oikawa, "Phase Corrected Total Variation for Audio Signals", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3093. Accessed: Apr. 21, 2018.
@article{3093-18,
url = {http://sigport.org/3093},
author = {Kohei Yatabe; Yasuhiro Oikawa },
publisher = {IEEE SigPort},
title = {Phase Corrected Total Variation for Audio Signals},
year = {2018} }
TY - EJOUR
T1 - Phase Corrected Total Variation for Audio Signals
AU - Kohei Yatabe; Yasuhiro Oikawa
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3093
ER -
Kohei Yatabe, Yasuhiro Oikawa. (2018). Phase Corrected Total Variation for Audio Signals. IEEE SigPort. http://sigport.org/3093
Kohei Yatabe, Yasuhiro Oikawa, 2018. Phase Corrected Total Variation for Audio Signals. Available at: http://sigport.org/3093.
Kohei Yatabe, Yasuhiro Oikawa. (2018). "Phase Corrected Total Variation for Audio Signals." Web.
1. Kohei Yatabe, Yasuhiro Oikawa. Phase Corrected Total Variation for Audio Signals [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3093

SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR


The non-homogeneous Poisson process (NHPP) is a point process with time-varying intensity across its domain, the use of which arises in numerous domains in signal processing, machine learning and many other fields. However, its applications are largely limited by the intractable likelihood and the high computational cost of existing inference schemes. We present an online inference framework that utilises generative Poisson data and sequential Markov Chain Monte Carlo (SMCMC) algorithm, which achieves improved performance in both synthetic and real datasets.

Paper Details

Authors:
Chenhao Li, Simon J. Godsill
Submitted On:
20 April 2018 - 4:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Sequential Methods for Non-homogeneous Poisson Intensity Inference

(5 downloads)

Keywords

Subscribe

[1] Chenhao Li, Simon J. Godsill, "SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3092. Accessed: Apr. 21, 2018.
@article{3092-18,
url = {http://sigport.org/3092},
author = {Chenhao Li; Simon J. Godsill },
publisher = {IEEE SigPort},
title = {SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR},
year = {2018} }
TY - EJOUR
T1 - SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR
AU - Chenhao Li; Simon J. Godsill
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3092
ER -
Chenhao Li, Simon J. Godsill. (2018). SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR. IEEE SigPort. http://sigport.org/3092
Chenhao Li, Simon J. Godsill, 2018. SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR. Available at: http://sigport.org/3092.
Chenhao Li, Simon J. Godsill. (2018). "SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR." Web.
1. Chenhao Li, Simon J. Godsill. SEQUENTIAL INFERENCE METHODS FOR NON-HOMGENEOUS POISSON PROCESSES WITH STATE-SPACE PRIOR [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3092

END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM

Paper Details

Authors:
Ivan Fung, Brian Mak
Submitted On:
20 April 2018 - 3:22am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

real_gray240.pdf

(7 downloads)

Keywords

Subscribe

[1] Ivan Fung, Brian Mak, "END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3091. Accessed: Apr. 21, 2018.
@article{3091-18,
url = {http://sigport.org/3091},
author = {Ivan Fung; Brian Mak },
publisher = {IEEE SigPort},
title = {END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM},
year = {2018} }
TY - EJOUR
T1 - END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM
AU - Ivan Fung; Brian Mak
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3091
ER -
Ivan Fung, Brian Mak. (2018). END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM. IEEE SigPort. http://sigport.org/3091
Ivan Fung, Brian Mak, 2018. END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM. Available at: http://sigport.org/3091.
Ivan Fung, Brian Mak. (2018). "END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM." Web.
1. Ivan Fung, Brian Mak. END-TO-END LOW-RESOURCE LIP-READING WITH MAXOUT CNN AND LSTM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3091

A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES

Paper Details

Authors:
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen
Submitted On:
20 April 2018 - 3:14am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Amir Hossein Poorjam, SNR estimation

(5 downloads)

Keywords

Subscribe

[1] Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen, "A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3090. Accessed: Apr. 21, 2018.
@article{3090-18,
url = {http://sigport.org/3090},
author = {Amir Hossein Poorjam; Max A. Little; Jesper Rindom Jensen; Mads Græsbøll Christensen },
publisher = {IEEE SigPort},
title = {A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES},
year = {2018} }
TY - EJOUR
T1 - A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES
AU - Amir Hossein Poorjam; Max A. Little; Jesper Rindom Jensen; Mads Græsbøll Christensen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3090
ER -
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen. (2018). A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES. IEEE SigPort. http://sigport.org/3090
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen, 2018. A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES. Available at: http://sigport.org/3090.
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen. (2018). "A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES." Web.
1. Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen. A SUPERVISED APPROACH TO GLOBAL SIGNAL-TO-NOISE RATIO ESTIMATION FOR WHISPERED AND PATHOLOGICAL VOICES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3090

A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES

Paper Details

Authors:
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen
Submitted On:
20 April 2018 - 3:11am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Amir Hossein Poorjam

(3 downloads)

Keywords

Subscribe

[1] Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen, "A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3089. Accessed: Apr. 21, 2018.
@article{3089-18,
url = {http://sigport.org/3089},
author = {Amir Hossein Poorjam; Max A. Little; Jesper Rindom Jensen; Mads Græsbøll Christensen },
publisher = {IEEE SigPort},
title = {A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES},
year = {2018} }
TY - EJOUR
T1 - A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES
AU - Amir Hossein Poorjam; Max A. Little; Jesper Rindom Jensen; Mads Græsbøll Christensen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3089
ER -
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen. (2018). A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES. IEEE SigPort. http://sigport.org/3089
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen, 2018. A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES. Available at: http://sigport.org/3089.
Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen. (2018). "A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES." Web.
1. Amir Hossein Poorjam, Max A. Little, Jesper Rindom Jensen, Mads Græsbøll Christensen. A PARAMETRIC APPROACH FOR CLASSIFICATION OF DISTORTIONS IN PATHOLOGICAL VOICES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3089

Pages