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

Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition


In this paper, we experiment with the recently introduced subword regularization technique \cite{kudo2018subword} in the context of end-to-end automatic speech recognition (ASR). We present results from both attention-based and CTC-based ASR systems on two common benchmark datasets, the 80 hour Wall Street Journal corpus and 1,000 hour Librispeech corpus. We also introduce a novel subword beam search decoding algorithm that significantly improves the final performance of the CTC-based systems.

Paper Details

Authors:
Jennifer Drexler, James Glass
Submitted On:
14 May 2019 - 9:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_poster_final.pdf

(4)

Subscribe

[1] Jennifer Drexler, James Glass, "Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4509. Accessed: May. 23, 2019.
@article{4509-19,
url = {http://sigport.org/4509},
author = {Jennifer Drexler; James Glass },
publisher = {IEEE SigPort},
title = {Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition},
year = {2019} }
TY - EJOUR
T1 - Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition
AU - Jennifer Drexler; James Glass
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4509
ER -
Jennifer Drexler, James Glass. (2019). Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition. IEEE SigPort. http://sigport.org/4509
Jennifer Drexler, James Glass, 2019. Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition. Available at: http://sigport.org/4509.
Jennifer Drexler, James Glass. (2019). "Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition." Web.
1. Jennifer Drexler, James Glass. Subword Regularization and Beam Search Decoding for End-to-End Automatic Speech Recognition [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4509

AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS


In recent years, the number and variety of heterogeneous multiprocessor system-on-chip MPSoCs, such as for instance Zynq platforms, has sensibly increased. However, today all design flow solutions capable of programming the different components of such platforms require to the designer either to modify the software or hardware based designs to obtain higher performance implementations. Thus, the developer needs to either rewrite functional blocks in HDL or to use high-level synthesis of C-like sequential languages with platform locked extensions.

Paper Details

Authors:
Simone Casale Brunet, Romuald Mosqueron, Marco Mattavelli
Submitted On:
14 May 2019 - 8:07am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

main-poster.pdf

(0)

Subscribe

[1] Simone Casale Brunet, Romuald Mosqueron, Marco Mattavelli, "AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4508. Accessed: May. 23, 2019.
@article{4508-19,
url = {http://sigport.org/4508},
author = {Simone Casale Brunet; Romuald Mosqueron; Marco Mattavelli },
publisher = {IEEE SigPort},
title = {AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS},
year = {2019} }
TY - EJOUR
T1 - AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS
AU - Simone Casale Brunet; Romuald Mosqueron; Marco Mattavelli
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4508
ER -
Simone Casale Brunet, Romuald Mosqueron, Marco Mattavelli. (2019). AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS. IEEE SigPort. http://sigport.org/4508
Simone Casale Brunet, Romuald Mosqueron, Marco Mattavelli, 2019. AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS. Available at: http://sigport.org/4508.
Simone Casale Brunet, Romuald Mosqueron, Marco Mattavelli. (2019). "AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS." Web.
1. Simone Casale Brunet, Romuald Mosqueron, Marco Mattavelli. AN HETEROGENEOUS COMPILER OF DATAFLOW PROGRAMS FOR ZYNQ PLATFORMS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4508

ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION

Paper Details

Authors:
Karen Livescu, Michael Picheny
Submitted On:
14 May 2019 - 7:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_official_final.pdf

(5)

Subscribe

[1] Karen Livescu, Michael Picheny, "ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4506. Accessed: May. 23, 2019.
@article{4506-19,
url = {http://sigport.org/4506},
author = {Karen Livescu; Michael Picheny },
publisher = {IEEE SigPort},
title = {ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION
AU - Karen Livescu; Michael Picheny
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4506
ER -
Karen Livescu, Michael Picheny. (2019). ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION. IEEE SigPort. http://sigport.org/4506
Karen Livescu, Michael Picheny, 2019. ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION. Available at: http://sigport.org/4506.
Karen Livescu, Michael Picheny. (2019). "ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION." Web.
1. Karen Livescu, Michael Picheny. ACOUSTICALLY GROUNDED WORD EMBEDDINGS FOR IMPROVED ACOUSTICS-TO-WORD SPEECH RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4506

DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS


The huge volume of data that are available today requires data-
selective processing approaches that avoid the costs in computa-
tional complexity via appropriately treating the non-innovative data.
In this paper, extensions of the well-known adaptive filtering LMS-
Newton and LMS-Quasi-Newton Algorithms are developed that
enable data selection while also addressing the censorship of out-
liers that emerge due to high measurement errors. The proposed
solutions allow the prescription of how often the acquired data are

Paper Details

Authors:
Submitted On:
14 May 2019 - 5:42am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

presentation_tsinos.pdf

(1)

Subscribe

[1] , "DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4505. Accessed: May. 23, 2019.
@article{4505-19,
url = {http://sigport.org/4505},
author = { },
publisher = {IEEE SigPort},
title = {DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS},
year = {2019} }
TY - EJOUR
T1 - DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4505
ER -
. (2019). DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS. IEEE SigPort. http://sigport.org/4505
, 2019. DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS. Available at: http://sigport.org/4505.
. (2019). "DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS." Web.
1. . DATA-SELECTIVE LMS-NEWTON AND LMS-QUASI-NEWTON ALGORITHMS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4505

AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION


Despite the recent success of multi-modal action recognition in videos, in reality, we usually confront the situation that some data are not available beforehand, especially for multimodal data. For example, while vision and audio data are required to address the multi-modal action recognition, audio tracks in videos are easily lost due to the broken files or the limitation of devices. To cope with this sound-missing problem, we present an approach to simulating deep audio feature from merely spatial-temporal vision data.

Paper Details

Authors:
Hu-Cheng Lee, Chih-Yu Lin, Pin-Chun Hsu, Winston H. Hsu
Submitted On:
14 May 2019 - 5:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

20190516_AUDIO_FEATURE_GENERATION_FOR_MISSING_MODALITY_PROBLEM_IN_VIDEO_ACTION_RECOGNITION.pptx

(1)

Subscribe

[1] Hu-Cheng Lee, Chih-Yu Lin, Pin-Chun Hsu, Winston H. Hsu, "AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4504. Accessed: May. 23, 2019.
@article{4504-19,
url = {http://sigport.org/4504},
author = {Hu-Cheng Lee; Chih-Yu Lin; Pin-Chun Hsu; Winston H. Hsu },
publisher = {IEEE SigPort},
title = {AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION
AU - Hu-Cheng Lee; Chih-Yu Lin; Pin-Chun Hsu; Winston H. Hsu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4504
ER -
Hu-Cheng Lee, Chih-Yu Lin, Pin-Chun Hsu, Winston H. Hsu. (2019). AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION. IEEE SigPort. http://sigport.org/4504
Hu-Cheng Lee, Chih-Yu Lin, Pin-Chun Hsu, Winston H. Hsu, 2019. AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION. Available at: http://sigport.org/4504.
Hu-Cheng Lee, Chih-Yu Lin, Pin-Chun Hsu, Winston H. Hsu. (2019). "AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION." Web.
1. Hu-Cheng Lee, Chih-Yu Lin, Pin-Chun Hsu, Winston H. Hsu. AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4504

Peak Detection and Baseline Correction using a Convolution Neural Network

Paper Details

Authors:
Mikkel N. Schmidt, Tommy S. Alstrøm, Marcus Svendstorp, Jan Larsen
Submitted On:
14 May 2019 - 7:46am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MLSP-L1.1_Alstrom_Tommy.pdf

(3)

Subscribe

[1] Mikkel N. Schmidt, Tommy S. Alstrøm, Marcus Svendstorp, Jan Larsen, "Peak Detection and Baseline Correction using a Convolution Neural Network", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4503. Accessed: May. 23, 2019.
@article{4503-19,
url = {http://sigport.org/4503},
author = {Mikkel N. Schmidt; Tommy S. Alstrøm; Marcus Svendstorp; Jan Larsen },
publisher = {IEEE SigPort},
title = {Peak Detection and Baseline Correction using a Convolution Neural Network},
year = {2019} }
TY - EJOUR
T1 - Peak Detection and Baseline Correction using a Convolution Neural Network
AU - Mikkel N. Schmidt; Tommy S. Alstrøm; Marcus Svendstorp; Jan Larsen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4503
ER -
Mikkel N. Schmidt, Tommy S. Alstrøm, Marcus Svendstorp, Jan Larsen. (2019). Peak Detection and Baseline Correction using a Convolution Neural Network. IEEE SigPort. http://sigport.org/4503
Mikkel N. Schmidt, Tommy S. Alstrøm, Marcus Svendstorp, Jan Larsen, 2019. Peak Detection and Baseline Correction using a Convolution Neural Network. Available at: http://sigport.org/4503.
Mikkel N. Schmidt, Tommy S. Alstrøm, Marcus Svendstorp, Jan Larsen. (2019). "Peak Detection and Baseline Correction using a Convolution Neural Network." Web.
1. Mikkel N. Schmidt, Tommy S. Alstrøm, Marcus Svendstorp, Jan Larsen. Peak Detection and Baseline Correction using a Convolution Neural Network [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4503

PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR

Paper Details

Authors:
Submitted On:
14 May 2019 - 3:25am
Short Link:
Type:
Event:

Document Files

PAPB_icassp-expanded-v2.pdf

(1)

Subscribe

[1] , "PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4502. Accessed: May. 23, 2019.
@article{4502-19,
url = {http://sigport.org/4502},
author = { },
publisher = {IEEE SigPort},
title = {PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR},
year = {2019} }
TY - EJOUR
T1 - PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4502
ER -
. (2019). PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR. IEEE SigPort. http://sigport.org/4502
, 2019. PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR. Available at: http://sigport.org/4502.
. (2019). "PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR." Web.
1. . PROMISING ACCURATE PREFIX BOOSTING FOR SEQUENCE-TO-SEQUENCE ASR [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4502

BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING


The intelligibility of speech in noise can be improved by modifying the speech. But with object-based audio, there
is the possibility of altering the background sound while leaving the speech unaltered. This may prove a less intrusive approach, affording good speech intelligibility without overly compromising the perceived sound quality. In this

Paper Details

Authors:
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang
Submitted On:
14 May 2019 - 2:49am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_TJC.pdf

(2)

Subscribe

[1] Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang, "BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4501. Accessed: May. 23, 2019.
@article{4501-19,
url = {http://sigport.org/4501},
author = {Yan Tang; Qingju Liu; Bruno Fazenda; Weuwu Wang },
publisher = {IEEE SigPort},
title = {BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING},
year = {2019} }
TY - EJOUR
T1 - BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING
AU - Yan Tang; Qingju Liu; Bruno Fazenda; Weuwu Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4501
ER -
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang. (2019). BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING. IEEE SigPort. http://sigport.org/4501
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang, 2019. BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING. Available at: http://sigport.org/4501.
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang. (2019). "BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING." Web.
1. Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang. BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4501

ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS


In this paper we compare the quality of synthesized views produced by four DIBR methods when fed by depth maps estimated by five state-of-the-art stereo matching algorithms. Also, we compute the correlation between four popular metrics for ranking stereo matching algorithms and two metrics commonly used to evaluate synthesized views (PSNR and SSIM) plus one specific for DIBR.

Paper Details

Authors:
Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung
Submitted On:
13 May 2019 - 9:19pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS

(5)

Subscribe

[1] Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung, "ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4499. Accessed: May. 23, 2019.
@article{4499-19,
url = {http://sigport.org/4499},
author = {Adriano Quilião de Oliveira; Thiago Lopes Trugillo da Silveira; Marcelo Walter; Cláudio Rosito Jung },
publisher = {IEEE SigPort},
title = {ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS},
year = {2019} }
TY - EJOUR
T1 - ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS
AU - Adriano Quilião de Oliveira; Thiago Lopes Trugillo da Silveira; Marcelo Walter; Cláudio Rosito Jung
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4499
ER -
Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung. (2019). ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS. IEEE SigPort. http://sigport.org/4499
Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung, 2019. ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS. Available at: http://sigport.org/4499.
Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung. (2019). "ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS." Web.
1. Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung. ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4499

A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties


Stochastic mirror descent (SMD) algorithms have recently garnered a great deal of attention in optimization, signal processing, and machine learning. They are similar to stochastic gradient descent (SGD), in that they perform updates along the negative gradient of an instantaneous (or stochastically chosen) loss function. However, rather than update the parameter (or weight) vector directly, they update it in a "mirrored" domain whose transformation is given by the gradient of a strictly convex differentiable potential function.

Paper Details

Authors:
Navid Azizan, Babak Hassibi
Submitted On:
13 May 2019 - 8:33pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP-SMD-Poster.pdf

(7)

Subscribe

[1] Navid Azizan, Babak Hassibi, "A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4498. Accessed: May. 23, 2019.
@article{4498-19,
url = {http://sigport.org/4498},
author = {Navid Azizan; Babak Hassibi },
publisher = {IEEE SigPort},
title = {A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties},
year = {2019} }
TY - EJOUR
T1 - A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties
AU - Navid Azizan; Babak Hassibi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4498
ER -
Navid Azizan, Babak Hassibi. (2019). A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties. IEEE SigPort. http://sigport.org/4498
Navid Azizan, Babak Hassibi, 2019. A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties. Available at: http://sigport.org/4498.
Navid Azizan, Babak Hassibi. (2019). "A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties." Web.
1. Navid Azizan, Babak Hassibi. A Characterization of Stochastic Mirror Descent Algorithms and Their Convergence Properties [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4498

Pages