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.

ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING

Paper Details

Authors:
An Dang, Toan Vu, Jia-Ching Wang
Submitted On:
17 April 2020 - 4:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2020.pdf

(51)

Subscribe

[1] An Dang, Toan Vu, Jia-Ching Wang, "ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5102. Accessed: Aug. 05, 2020.
@article{5102-20,
url = {http://sigport.org/5102},
author = {An Dang; Toan Vu; Jia-Ching Wang },
publisher = {IEEE SigPort},
title = {ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING},
year = {2020} }
TY - EJOUR
T1 - ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING
AU - An Dang; Toan Vu; Jia-Ching Wang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5102
ER -
An Dang, Toan Vu, Jia-Ching Wang. (2020). ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING. IEEE SigPort. http://sigport.org/5102
An Dang, Toan Vu, Jia-Ching Wang, 2020. ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING. Available at: http://sigport.org/5102.
An Dang, Toan Vu, Jia-Ching Wang. (2020). "ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING." Web.
1. An Dang, Toan Vu, Jia-Ching Wang. ENCODER-RECURRENT DECODER NETWORK FOR SINGLE IMAGE DEHAZING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5102

Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method


In image quality assessments, the results of subjective evaluation experiments that use the double-stimulus impairment scale (DSIS) method are often expressed in terms of the mean opinion score (MOS), which is the average score of all subjects for each test condition. Some MOS values are used to derive image quality criteria, and it has been assumed that it is preferable to perform tests with non-expert subjects rather than with experts. In this study, we analyze the results of several subjective evaluation experiments using the DSIS method.

Paper Details

Authors:
Marcelo Bertalmío
Submitted On:
17 April 2020 - 2:28am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

20200504_ICASSP.pdf

(39)

Subscribe

[1] Marcelo Bertalmío, "Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5101. Accessed: Aug. 05, 2020.
@article{5101-20,
url = {http://sigport.org/5101},
author = {Marcelo Bertalmío },
publisher = {IEEE SigPort},
title = {Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method},
year = {2020} }
TY - EJOUR
T1 - Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method
AU - Marcelo Bertalmío
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5101
ER -
Marcelo Bertalmío. (2020). Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method. IEEE SigPort. http://sigport.org/5101
Marcelo Bertalmío, 2020. Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method. Available at: http://sigport.org/5101.
Marcelo Bertalmío. (2020). "Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method." Web.
1. Marcelo Bertalmío. Non-Experts or Experts? Statistical Analyses of MOS using DSIS Method [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5101

Key Action And Joint CTC-Attention Based Sign Language Recognition


Sign Language Recognition (SLR) translates sign language video into natural language. In practice, sign language video, owning a large number of redundant frames, is necessary to be selected the essential. However, unlike common video that describes actions, sign language video is characterized as continuous and dense action sequence, which is difficult to capture key actions corresponding to meaningful sentence. In this paper, we propose to hierarchically search key actions by a pyramid BiLSTM.

Paper Details

Authors:
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng
Submitted On:
16 April 2020 - 11:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_video5717.pdf

(39)

Subscribe

[1] Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, "Key Action And Joint CTC-Attention Based Sign Language Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5100. Accessed: Aug. 05, 2020.
@article{5100-20,
url = {http://sigport.org/5100},
author = {Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng },
publisher = {IEEE SigPort},
title = {Key Action And Joint CTC-Attention Based Sign Language Recognition},
year = {2020} }
TY - EJOUR
T1 - Key Action And Joint CTC-Attention Based Sign Language Recognition
AU - Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5100
ER -
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). Key Action And Joint CTC-Attention Based Sign Language Recognition. IEEE SigPort. http://sigport.org/5100
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, 2020. Key Action And Joint CTC-Attention Based Sign Language Recognition. Available at: http://sigport.org/5100.
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). "Key Action And Joint CTC-Attention Based Sign Language Recognition." Web.
1. Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. Key Action And Joint CTC-Attention Based Sign Language Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5100

Key Action And Joint CTC-Attention Based Sign Language Recognition


Sign Language Recognition (SLR) translates sign language video into natural language. In practice, sign language video, owning a large number of redundant frames, is necessary to be selected the essential. However, unlike common video that describes actions, sign language video is characterized as continuous and dense action sequence, which is difficult to capture key actions corresponding to meaningful sentence. In this paper, we propose to hierarchically search key actions by a pyramid BiLSTM.

Paper Details

Authors:
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng
Submitted On:
16 April 2020 - 11:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_video5717.pdf

(57)

Subscribe

[1] Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, "Key Action And Joint CTC-Attention Based Sign Language Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5099. Accessed: Aug. 05, 2020.
@article{5099-20,
url = {http://sigport.org/5099},
author = {Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng },
publisher = {IEEE SigPort},
title = {Key Action And Joint CTC-Attention Based Sign Language Recognition},
year = {2020} }
TY - EJOUR
T1 - Key Action And Joint CTC-Attention Based Sign Language Recognition
AU - Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5099
ER -
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). Key Action And Joint CTC-Attention Based Sign Language Recognition. IEEE SigPort. http://sigport.org/5099
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, 2020. Key Action And Joint CTC-Attention Based Sign Language Recognition. Available at: http://sigport.org/5099.
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). "Key Action And Joint CTC-Attention Based Sign Language Recognition." Web.
1. Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. Key Action And Joint CTC-Attention Based Sign Language Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5099

Estimating Structural Missing Values via Low-tubal-rank Tensor Completion


The recently proposed Tensor Nuclear Norm (TNN) minimization has been widely used for tensor completion. However, previous works didn’t consider the structural difference between the observed data and missing data, which widely exists in many applications. In this paper, we propose to incorporate a constraint item on the missing values into low-tubal-rank tensor completion to promote the structural hypothesis

Paper Details

Authors:
Hailin Wang, Feng Zhang, Jianjun Wang, Yao Wang
Submitted On:
16 April 2020 - 3:15am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Estimating Structural Missing Values via Low-tubal-rank Tensor Completion.pdf

(44)

Keywords

Additional Categories

Subscribe

[1] Hailin Wang, Feng Zhang, Jianjun Wang, Yao Wang, "Estimating Structural Missing Values via Low-tubal-rank Tensor Completion", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5098. Accessed: Aug. 05, 2020.
@article{5098-20,
url = {http://sigport.org/5098},
author = {Hailin Wang; Feng Zhang; Jianjun Wang; Yao Wang },
publisher = {IEEE SigPort},
title = {Estimating Structural Missing Values via Low-tubal-rank Tensor Completion},
year = {2020} }
TY - EJOUR
T1 - Estimating Structural Missing Values via Low-tubal-rank Tensor Completion
AU - Hailin Wang; Feng Zhang; Jianjun Wang; Yao Wang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5098
ER -
Hailin Wang, Feng Zhang, Jianjun Wang, Yao Wang. (2020). Estimating Structural Missing Values via Low-tubal-rank Tensor Completion. IEEE SigPort. http://sigport.org/5098
Hailin Wang, Feng Zhang, Jianjun Wang, Yao Wang, 2020. Estimating Structural Missing Values via Low-tubal-rank Tensor Completion. Available at: http://sigport.org/5098.
Hailin Wang, Feng Zhang, Jianjun Wang, Yao Wang. (2020). "Estimating Structural Missing Values via Low-tubal-rank Tensor Completion." Web.
1. Hailin Wang, Feng Zhang, Jianjun Wang, Yao Wang. Estimating Structural Missing Values via Low-tubal-rank Tensor Completion [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5098

A Sequence Matching Network for Polyphonic Sound Event Localization and Detection


Polyphonic sound event detection and direction-of-arrival estimation require different input features from audio signals. While sound event detection mainly relies on time-frequency patterns, direction-of-arrival estimation relies on magnitude or phase differences between microphones. Previous approaches use the same input features for sound event detection and direction-of-arrival estimation, and train the two tasks jointly or in a two-stage transfer-learning manner.

Paper Details

Authors:
T. N. T. Nguyen, D. L. Jones, W. S. Gan
Submitted On:
23 April 2020 - 4:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2020 - Tho Nguyen - NTU - Sequence Matching - Sigpost.pdf

(44)

Subscribe

[1] T. N. T. Nguyen, D. L. Jones, W. S. Gan, "A Sequence Matching Network for Polyphonic Sound Event Localization and Detection", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5096. Accessed: Aug. 05, 2020.
@article{5096-20,
url = {http://sigport.org/5096},
author = {T. N. T. Nguyen; D. L. Jones; W. S. Gan },
publisher = {IEEE SigPort},
title = {A Sequence Matching Network for Polyphonic Sound Event Localization and Detection},
year = {2020} }
TY - EJOUR
T1 - A Sequence Matching Network for Polyphonic Sound Event Localization and Detection
AU - T. N. T. Nguyen; D. L. Jones; W. S. Gan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5096
ER -
T. N. T. Nguyen, D. L. Jones, W. S. Gan. (2020). A Sequence Matching Network for Polyphonic Sound Event Localization and Detection. IEEE SigPort. http://sigport.org/5096
T. N. T. Nguyen, D. L. Jones, W. S. Gan, 2020. A Sequence Matching Network for Polyphonic Sound Event Localization and Detection. Available at: http://sigport.org/5096.
T. N. T. Nguyen, D. L. Jones, W. S. Gan. (2020). "A Sequence Matching Network for Polyphonic Sound Event Localization and Detection." Web.
1. T. N. T. Nguyen, D. L. Jones, W. S. Gan. A Sequence Matching Network for Polyphonic Sound Event Localization and Detection [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5096

AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES


This paper presents an improved deep embedding learning method based on a convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) a multiscale convolution (MSCNN) is adopted in the frame-level layers to capture the complementary speaker information in different receptive fields; (2) a Baum-Welch statistics attention (BWSA) mechanism is applied in the pooling layer, which can integrate more useful long-term speaker characteristics in the temporal pooling layer.

Paper Details

Authors:
Submitted On:
14 April 2020 - 6:25am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2020_poster_BinGu.pdf

(35)

Subscribe

[1] , "AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5095. Accessed: Aug. 05, 2020.
@article{5095-20,
url = {http://sigport.org/5095},
author = { },
publisher = {IEEE SigPort},
title = {AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES},
year = {2020} }
TY - EJOUR
T1 - AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5095
ER -
. (2020). AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES. IEEE SigPort. http://sigport.org/5095
, 2020. AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES. Available at: http://sigport.org/5095.
. (2020). "AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES." Web.
1. . AN IMPROVED DEEP NEURAL NETWORK FOR MODELING SPEAKER CHARACTERISTICS AT DIFFERENT TEMPORAL SCALES [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5095

Source Coding of Audio Signals with a Generative Model


We consider source coding of audio signals with the help of a generative model. We use a construction where a waveform is first quantized, yielding a finite bitrate representation. The waveform is then reconstructed by random sampling from a model conditioned on the quantized waveform. The proposed coding scheme is theoretically analyzed. Using SampleRNN as the generative model, we demonstrate that the proposed coding structure provides performance competitive with state-of-the-art source coding tools for specific categories of audio signals.

Paper Details

Authors:
Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou
Submitted On:
14 April 2020 - 5:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

SourceCodingOfAudioSignals_ICASSP2020_demo.zip

(50)

Subscribe

[1] Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou, "Source Coding of Audio Signals with a Generative Model", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5094. Accessed: Aug. 05, 2020.
@article{5094-20,
url = {http://sigport.org/5094},
author = {Roy Fejgin; Janusz Klejsa; Lars Villemoes; Cong Zhou },
publisher = {IEEE SigPort},
title = {Source Coding of Audio Signals with a Generative Model},
year = {2020} }
TY - EJOUR
T1 - Source Coding of Audio Signals with a Generative Model
AU - Roy Fejgin; Janusz Klejsa; Lars Villemoes; Cong Zhou
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5094
ER -
Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou. (2020). Source Coding of Audio Signals with a Generative Model. IEEE SigPort. http://sigport.org/5094
Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou, 2020. Source Coding of Audio Signals with a Generative Model. Available at: http://sigport.org/5094.
Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou. (2020). "Source Coding of Audio Signals with a Generative Model." Web.
1. Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou. Source Coding of Audio Signals with a Generative Model [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5094

SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION


Spectrograms fusion is an effective method for incorporating complementary speech dereverberation systems. Previous linear spectrograms fusion by averaging multiple spectrograms shows outstanding performance. However, various systems with different features cannot apply this simple method. In this study, we design the minimum difference masks (MDMs) to classify the time-frequency (T-F) bins in spectrograms according to the nearest distances from labels. Then, we propose a two-stage nonlinear spectrograms fusion system for speech dereverberation.

Paper Details

Authors:
Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, Jianwu Dang
Submitted On:
14 April 2020 - 4:41am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

3378-ICASSP-2020-poster-shi

(38)

Subscribe

[1] Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, Jianwu Dang, "SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5093. Accessed: Aug. 05, 2020.
@article{5093-20,
url = {http://sigport.org/5093},
author = {Hao Shi; Longbiao Wang; Meng Ge; Sheng Li; Jianwu Dang },
publisher = {IEEE SigPort},
title = {SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION},
year = {2020} }
TY - EJOUR
T1 - SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION
AU - Hao Shi; Longbiao Wang; Meng Ge; Sheng Li; Jianwu Dang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5093
ER -
Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, Jianwu Dang. (2020). SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION. IEEE SigPort. http://sigport.org/5093
Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, Jianwu Dang, 2020. SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION. Available at: http://sigport.org/5093.
Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, Jianwu Dang. (2020). "SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION." Web.
1. Hao Shi, Longbiao Wang, Meng Ge, Sheng Li, Jianwu Dang. SPECTROGRAMS FUSION WITH MINIMUM DIFFERENCE MASKS ESTIMATION FOR MONAURAL SPEECH DEREVERBERATION [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5093

Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking


In this paper, we extend previous particle filtering methods whose states were constrained to the (real) Stiefel manifold to the complex case. The method is then applied to a Bayesian formulation of the subspace tracking problem. To implement the proposed particle filter, we modify a previous MCMC algorithm so as to simulate from densities defined on the complex manifold. Also, to compute subspace estimates from particle approximations, we extend existing averaging methods to complex Grassmannians.

Paper Details

Authors:
Marcelo G. S. Bruno
Submitted On:
13 April 2020 - 9:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides

(37)

Subscribe

[1] Marcelo G. S. Bruno, "Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5092. Accessed: Aug. 05, 2020.
@article{5092-20,
url = {http://sigport.org/5092},
author = {Marcelo G. S. Bruno },
publisher = {IEEE SigPort},
title = {Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking},
year = {2020} }
TY - EJOUR
T1 - Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking
AU - Marcelo G. S. Bruno
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5092
ER -
Marcelo G. S. Bruno. (2020). Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking. IEEE SigPort. http://sigport.org/5092
Marcelo G. S. Bruno, 2020. Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking. Available at: http://sigport.org/5092.
Marcelo G. S. Bruno. (2020). "Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking." Web.
1. Marcelo G. S. Bruno. Particle Filtering on the Complex Stiefel Manifold with Application to Subspace Tracking [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5092

Pages