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.

A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING


Neural network language model (NNLM) is an essential component of industrial ASR systems. One important challenge of training an NNLM is to leverage between scaling the learning process and handling big data. Conventional approaches such as block momentum provides a blockwise model update filtering (BMUF) process and achieves almost linear speedups with no performance degradation for speech recognition.

Paper Details

Authors:
Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu
Submitted On:
12 March 2020 - 9:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

gossip-BMUF

(61)

Subscribe

[1] Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu, "A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4996. Accessed: Aug. 06, 2020.
@article{4996-20,
url = {http://sigport.org/4996},
author = {Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu },
publisher = {IEEE SigPort},
title = {A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING},
year = {2020} }
TY - EJOUR
T1 - A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING
AU - Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4996
ER -
Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu. (2020). A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING. IEEE SigPort. http://sigport.org/4996
Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu, 2020. A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING. Available at: http://sigport.org/4996.
Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu. (2020). "A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING." Web.
1. Yiheng Huang; Jinchuan Tian; Lei Han; Guangsen Wang; Xingchen Song; Dan Su; Dong Yu. A RANDOM GOSSIP BMUF PROCESS FOR NEURAL LANGUAGE MODELING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4996

LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES


With the increasing of human space activities, the number of space debris has increased dramatically, the possibility that spacecraft in orbit is impacted by space debris is growing. It is important to detect and locate the gas leak accurately and timely. In this paper, a leak detection method using ultrasonic sensor array is proposed. Firstly, the ultrasonic sensor array is used to detect the leak acoustic signal which propagates as Lamb wave through spacecraft structure. Then we apply beam forming algorithm to determine the direction of the leak source.

Paper Details

Authors:
Lei Qi, Lichen Sun, Donghui Meng, Rongxin Yan, Wei Sun
Submitted On:
23 February 2020 - 3:59am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES.doc

(49)

Subscribe

[1] Lei Qi, Lichen Sun, Donghui Meng, Rongxin Yan, Wei Sun, "LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4993. Accessed: Aug. 06, 2020.
@article{4993-20,
url = {http://sigport.org/4993},
author = { Lei Qi; Lichen Sun; Donghui Meng; Rongxin Yan; Wei Sun },
publisher = {IEEE SigPort},
title = {LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES},
year = {2020} }
TY - EJOUR
T1 - LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES
AU - Lei Qi; Lichen Sun; Donghui Meng; Rongxin Yan; Wei Sun
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4993
ER -
Lei Qi, Lichen Sun, Donghui Meng, Rongxin Yan, Wei Sun. (2020). LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES. IEEE SigPort. http://sigport.org/4993
Lei Qi, Lichen Sun, Donghui Meng, Rongxin Yan, Wei Sun, 2020. LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES. Available at: http://sigport.org/4993.
Lei Qi, Lichen Sun, Donghui Meng, Rongxin Yan, Wei Sun. (2020). "LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES." Web.
1. Lei Qi, Lichen Sun, Donghui Meng, Rongxin Yan, Wei Sun. LEAK DETECTION OF SPACECRAFT IN ORBIT USING ULTRASONIC SENSOR ARRAY BY LAMB WAVES [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4993

ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION


In the treatment of epilepsy with intracranial electroencephalogram(iEEG), the recognition accuracy is low, and it is
difficult to find the correlation between channels because of the large amount of channel numbers and time series data. In
order to solve these problems, we propose a novel EEG feature prepresentation method for seizure detection based on the
Log Mel-Filterbank energy feature. We propose to adapt the Mel-Filterbank energy to EEG features with logrithm transform

Paper Details

Authors:
Danyang Wang, Yuchun Fang, Yifan Li
Submitted On:
16 February 2020 - 7:54pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster for ICASSP2020 Paper4161

(59)

Subscribe

[1] Danyang Wang, Yuchun Fang, Yifan Li, "ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4991. Accessed: Aug. 06, 2020.
@article{4991-20,
url = {http://sigport.org/4991},
author = {Danyang Wang; Yuchun Fang; Yifan Li },
publisher = {IEEE SigPort},
title = {ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION},
year = {2020} }
TY - EJOUR
T1 - ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION
AU - Danyang Wang; Yuchun Fang; Yifan Li
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4991
ER -
Danyang Wang, Yuchun Fang, Yifan Li. (2020). ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION. IEEE SigPort. http://sigport.org/4991
Danyang Wang, Yuchun Fang, Yifan Li, 2020. ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION. Available at: http://sigport.org/4991.
Danyang Wang, Yuchun Fang, Yifan Li. (2020). "ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION." Web.
1. Danyang Wang, Yuchun Fang, Yifan Li. ENHANCE FEATURE REPRESENTATION OF ELECTROENCEPHALOGRAM FOR SEIZURE DETECTION [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4991

Performance Bounds for Displaced Sensor Automotive Radar Imaging


In automotive radar imaging, displaced sensors offer improvement in localization accuracy by jointly processing the data acquired from multiple radar units, each of which may have limited individual resources. In this paper, we derive performance bounds on the estimation error of target parameters processed by displaced sensors that correspond to several independent radars mounted at different locations on the same vehicle. Unlike previous studies, we do not assume a very accurate time synchronization among the sensors.

Paper Details

Authors:
Submitted On:
15 February 2020 - 1:31am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2020_displacedSensors (10).pdf

(50)

Subscribe

[1] , "Performance Bounds for Displaced Sensor Automotive Radar Imaging", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4990. Accessed: Aug. 06, 2020.
@article{4990-20,
url = {http://sigport.org/4990},
author = { },
publisher = {IEEE SigPort},
title = {Performance Bounds for Displaced Sensor Automotive Radar Imaging},
year = {2020} }
TY - EJOUR
T1 - Performance Bounds for Displaced Sensor Automotive Radar Imaging
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4990
ER -
. (2020). Performance Bounds for Displaced Sensor Automotive Radar Imaging. IEEE SigPort. http://sigport.org/4990
, 2020. Performance Bounds for Displaced Sensor Automotive Radar Imaging. Available at: http://sigport.org/4990.
. (2020). "Performance Bounds for Displaced Sensor Automotive Radar Imaging." Web.
1. . Performance Bounds for Displaced Sensor Automotive Radar Imaging [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4990

An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets


This work outlines a method for an application of empirical Bayes in the setting of semi-supervised learning. That is, we consider a scenario in which the training set is partially or entirely unlabeled. In addition to the missing labels, we also consider a scenario where the available training data might be shuffled (i.e., the features and labels are not matched).

Paper Details

Authors:
Alex Dytso, H. Vincent Poor
Submitted On:
13 February 2020 - 3:22pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP.pdf

(73)

Keywords

Additional Categories

Subscribe

[1] Alex Dytso, H. Vincent Poor, "An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4989. Accessed: Aug. 06, 2020.
@article{4989-20,
url = {http://sigport.org/4989},
author = {Alex Dytso; H. Vincent Poor },
publisher = {IEEE SigPort},
title = {An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets},
year = {2020} }
TY - EJOUR
T1 - An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets
AU - Alex Dytso; H. Vincent Poor
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4989
ER -
Alex Dytso, H. Vincent Poor. (2020). An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets. IEEE SigPort. http://sigport.org/4989
Alex Dytso, H. Vincent Poor, 2020. An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets. Available at: http://sigport.org/4989.
Alex Dytso, H. Vincent Poor. (2020). "An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets." Web.
1. Alex Dytso, H. Vincent Poor. An Empirical Bayes Approach to Partially Labeled and Shuffled Data Sets [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4989

A Self-Attentive Emotion Recognition Network


Attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recognition in dyadic conversations. In this work, we introduce a novel attention mechanism capable of inferring the immensity of the effect of each past utterance on the current speaker emotional state.

Paper Details

Authors:
Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis
Submitted On:
13 February 2020 - 2:28pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster__A_Self_Attentive_Emotion_Recognition_Network.pdf

(49)

Subscribe

[1] Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis, "A Self-Attentive Emotion Recognition Network", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4988. Accessed: Aug. 06, 2020.
@article{4988-20,
url = {http://sigport.org/4988},
author = {Harris Partaourides; Kostantinos Papadamou; Nicolas Kourtellis; Ilias Leontiades; Sotirios Chatzis },
publisher = {IEEE SigPort},
title = {A Self-Attentive Emotion Recognition Network},
year = {2020} }
TY - EJOUR
T1 - A Self-Attentive Emotion Recognition Network
AU - Harris Partaourides; Kostantinos Papadamou; Nicolas Kourtellis; Ilias Leontiades; Sotirios Chatzis
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4988
ER -
Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis. (2020). A Self-Attentive Emotion Recognition Network. IEEE SigPort. http://sigport.org/4988
Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis, 2020. A Self-Attentive Emotion Recognition Network. Available at: http://sigport.org/4988.
Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis. (2020). "A Self-Attentive Emotion Recognition Network." Web.
1. Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis. A Self-Attentive Emotion Recognition Network [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4988

text-independent speaker verfication with adversarial learning on short utterances

Paper Details

Authors:
Kai Liu, Huan Zhou
Submitted On:
13 February 2020 - 11:17am
Short Link:
Type:
Event:
Paper Code:

Document Files

ICASSP paper #5822

(100)

Subscribe

[1] Kai Liu, Huan Zhou, "text-independent speaker verfication with adversarial learning on short utterances", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4987. Accessed: Aug. 06, 2020.
@article{4987-20,
url = {http://sigport.org/4987},
author = {Kai Liu; Huan Zhou },
publisher = {IEEE SigPort},
title = {text-independent speaker verfication with adversarial learning on short utterances},
year = {2020} }
TY - EJOUR
T1 - text-independent speaker verfication with adversarial learning on short utterances
AU - Kai Liu; Huan Zhou
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4987
ER -
Kai Liu, Huan Zhou. (2020). text-independent speaker verfication with adversarial learning on short utterances. IEEE SigPort. http://sigport.org/4987
Kai Liu, Huan Zhou, 2020. text-independent speaker verfication with adversarial learning on short utterances. Available at: http://sigport.org/4987.
Kai Liu, Huan Zhou. (2020). "text-independent speaker verfication with adversarial learning on short utterances." Web.
1. Kai Liu, Huan Zhou. text-independent speaker verfication with adversarial learning on short utterances [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4987

MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY


The widespread application of audio communication technologies has speeded up audio data flowing across the Internet, which made it an popular carrier for covert communication. In this paper, we present a cross-modal steganography method for hiding image content into audio carriers while preserving the perceptual fidelity of the cover audio.

Paper Details

Authors:
Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao
Submitted On:
13 February 2020 - 7:23am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster-MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY

(75)

Subscribe

[1] Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao, "MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4986. Accessed: Aug. 06, 2020.
@article{4986-20,
url = {http://sigport.org/4986},
author = {Wenxue Cui; Shaohui Liu; Feng Jiang; Yongliang Liu; Debin Zhao },
publisher = {IEEE SigPort},
title = {MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY},
year = {2020} }
TY - EJOUR
T1 - MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY
AU - Wenxue Cui; Shaohui Liu; Feng Jiang; Yongliang Liu; Debin Zhao
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4986
ER -
Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao. (2020). MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY. IEEE SigPort. http://sigport.org/4986
Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao, 2020. MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY. Available at: http://sigport.org/4986.
Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao. (2020). "MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY." Web.
1. Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao. MULTI-STAGE RESIDUAL HIDING FOR IMAGE-INTO-AUDIO STEGANOGRAPHY [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4986

Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors


Quantum computers threaten to break public-key cryptography schemes such as DSA and ECDSA in polynomial time, which poses an imminent threat to secure signal processing.
Ring learning with error (RLWE) lattice-based cryptography (LBC) is one of the most promising families of post-quantum cryptography (PQC) schemes in terms of efficiency and versatility. Two conventional methods to compute polynomial multiplication, the most compute-intensive routine in the RLWE schemes, are convolutions and Number Theoretic Transform (NTT).

Paper Details

Authors:
Hamid Nejatollahi, Sina Shahhosseini, Rosario Cammarota, Nikil Dutt
Submitted On:
12 February 2020 - 8:32pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2020_ICASSP-Camera_ready.pdf

(55)

Subscribe

[1] Hamid Nejatollahi, Sina Shahhosseini, Rosario Cammarota, Nikil Dutt, "Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4985. Accessed: Aug. 06, 2020.
@article{4985-20,
url = {http://sigport.org/4985},
author = {Hamid Nejatollahi; Sina Shahhosseini; Rosario Cammarota; Nikil Dutt },
publisher = {IEEE SigPort},
title = {Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors},
year = {2020} }
TY - EJOUR
T1 - Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors
AU - Hamid Nejatollahi; Sina Shahhosseini; Rosario Cammarota; Nikil Dutt
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4985
ER -
Hamid Nejatollahi, Sina Shahhosseini, Rosario Cammarota, Nikil Dutt. (2020). Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors. IEEE SigPort. http://sigport.org/4985
Hamid Nejatollahi, Sina Shahhosseini, Rosario Cammarota, Nikil Dutt, 2020. Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors. Available at: http://sigport.org/4985.
Hamid Nejatollahi, Sina Shahhosseini, Rosario Cammarota, Nikil Dutt. (2020). "Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors." Web.
1. Hamid Nejatollahi, Sina Shahhosseini, Rosario Cammarota, Nikil Dutt. Exploring Energy Efficient Quantum-resistant Signal Processing Using Array Processors [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4985

Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction

Paper Details

Authors:
Weiran Wang, Qingming Tang, Karen Livescu
Submitted On:
13 February 2020 - 6:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

main.pdf

(70)

Subscribe

[1] Weiran Wang, Qingming Tang, Karen Livescu, "Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4984. Accessed: Aug. 06, 2020.
@article{4984-20,
url = {http://sigport.org/4984},
author = {Weiran Wang; Qingming Tang; Karen Livescu },
publisher = {IEEE SigPort},
title = {Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction},
year = {2020} }
TY - EJOUR
T1 - Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction
AU - Weiran Wang; Qingming Tang; Karen Livescu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4984
ER -
Weiran Wang, Qingming Tang, Karen Livescu. (2020). Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction. IEEE SigPort. http://sigport.org/4984
Weiran Wang, Qingming Tang, Karen Livescu, 2020. Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction. Available at: http://sigport.org/4984.
Weiran Wang, Qingming Tang, Karen Livescu. (2020). "Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction." Web.
1. Weiran Wang, Qingming Tang, Karen Livescu. Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4984

Pages