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

Machine Learning for Signal Processing

Adversarial Speaker Adaptation


We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-dependent (SD) deep neural network (DNN) acoustic model to be close to that of a fixed speaker-independent (SI) DNN acoustic model during adaptation. An additional discriminator network is introduced to distinguish the deep features generated by the SD model from those produced by the SI model.

Paper Details

Authors:
Zhong Meng, Jinyu Li, Yifan Gong
Submitted On:
12 May 2019 - 9:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

asa_oral_v3.pptx

(81)

Subscribe

[1] Zhong Meng, Jinyu Li, Yifan Gong, "Adversarial Speaker Adaptation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4475. Accessed: Dec. 13, 2019.
@article{4475-19,
url = {http://sigport.org/4475},
author = {Zhong Meng; Jinyu Li; Yifan Gong },
publisher = {IEEE SigPort},
title = {Adversarial Speaker Adaptation},
year = {2019} }
TY - EJOUR
T1 - Adversarial Speaker Adaptation
AU - Zhong Meng; Jinyu Li; Yifan Gong
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4475
ER -
Zhong Meng, Jinyu Li, Yifan Gong. (2019). Adversarial Speaker Adaptation. IEEE SigPort. http://sigport.org/4475
Zhong Meng, Jinyu Li, Yifan Gong, 2019. Adversarial Speaker Adaptation. Available at: http://sigport.org/4475.
Zhong Meng, Jinyu Li, Yifan Gong. (2019). "Adversarial Speaker Adaptation." Web.
1. Zhong Meng, Jinyu Li, Yifan Gong. Adversarial Speaker Adaptation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4475

Attentive Adversarial Learning for Domain-Invariant Training


Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary domain classifier takes in equally-weighted deep features from a deep neural network (DNN) acoustic model and is trained to improve their domain-invariance by optimizing an adversarial loss function.

Paper Details

Authors:
Zhong Meng, Jinyu Li, Yifan Gong
Submitted On:
12 May 2019 - 9:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

aadit_poster.pptx

(53)

Subscribe

[1] Zhong Meng, Jinyu Li, Yifan Gong, "Attentive Adversarial Learning for Domain-Invariant Training", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4474. Accessed: Dec. 13, 2019.
@article{4474-19,
url = {http://sigport.org/4474},
author = {Zhong Meng; Jinyu Li; Yifan Gong },
publisher = {IEEE SigPort},
title = {Attentive Adversarial Learning for Domain-Invariant Training},
year = {2019} }
TY - EJOUR
T1 - Attentive Adversarial Learning for Domain-Invariant Training
AU - Zhong Meng; Jinyu Li; Yifan Gong
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4474
ER -
Zhong Meng, Jinyu Li, Yifan Gong. (2019). Attentive Adversarial Learning for Domain-Invariant Training. IEEE SigPort. http://sigport.org/4474
Zhong Meng, Jinyu Li, Yifan Gong, 2019. Attentive Adversarial Learning for Domain-Invariant Training. Available at: http://sigport.org/4474.
Zhong Meng, Jinyu Li, Yifan Gong. (2019). "Attentive Adversarial Learning for Domain-Invariant Training." Web.
1. Zhong Meng, Jinyu Li, Yifan Gong. Attentive Adversarial Learning for Domain-Invariant Training [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4474

Adversarial Speaker Verification


The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions. In this work, we propose an adversarial speaker verification (ASV) scheme to learn the condition-invariant deep embedding via adversarial multi-task training. In ASV, a speaker classification network and a condition identification network are jointly optimized to minimize the speaker classification loss and simultaneously mini-maximize the condition loss.

Paper Details

Authors:
Zhong Meng, Yong Zhao, Jinyu Li, Yifan Gong
Submitted On:
12 May 2019 - 9:24pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

asv_poster_v3.pptx

(63)

Subscribe

[1] Zhong Meng, Yong Zhao, Jinyu Li, Yifan Gong, "Adversarial Speaker Verification", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4473. Accessed: Dec. 13, 2019.
@article{4473-19,
url = {http://sigport.org/4473},
author = {Zhong Meng; Yong Zhao; Jinyu Li; Yifan Gong },
publisher = {IEEE SigPort},
title = {Adversarial Speaker Verification},
year = {2019} }
TY - EJOUR
T1 - Adversarial Speaker Verification
AU - Zhong Meng; Yong Zhao; Jinyu Li; Yifan Gong
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4473
ER -
Zhong Meng, Yong Zhao, Jinyu Li, Yifan Gong. (2019). Adversarial Speaker Verification. IEEE SigPort. http://sigport.org/4473
Zhong Meng, Yong Zhao, Jinyu Li, Yifan Gong, 2019. Adversarial Speaker Verification. Available at: http://sigport.org/4473.
Zhong Meng, Yong Zhao, Jinyu Li, Yifan Gong. (2019). "Adversarial Speaker Verification." Web.
1. Zhong Meng, Yong Zhao, Jinyu Li, Yifan Gong. Adversarial Speaker Verification [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4473

Conditional Teacher-Student Learning


The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is that a teacher model, not always perfect, sporadically produces wrong guidance in form of posterior probabilities that misleads the student model towards a suboptimal performance.

Paper Details

Authors:
Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong
Submitted On:
12 May 2019 - 9:23pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

cts_poster.pptx

(57)

Subscribe

[1] Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong, "Conditional Teacher-Student Learning", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4472. Accessed: Dec. 13, 2019.
@article{4472-19,
url = {http://sigport.org/4472},
author = {Zhong Meng; Jinyu Li; Yong Zhao; Yifan Gong },
publisher = {IEEE SigPort},
title = {Conditional Teacher-Student Learning},
year = {2019} }
TY - EJOUR
T1 - Conditional Teacher-Student Learning
AU - Zhong Meng; Jinyu Li; Yong Zhao; Yifan Gong
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4472
ER -
Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong. (2019). Conditional Teacher-Student Learning. IEEE SigPort. http://sigport.org/4472
Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong, 2019. Conditional Teacher-Student Learning. Available at: http://sigport.org/4472.
Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong. (2019). "Conditional Teacher-Student Learning." Web.
1. Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong. Conditional Teacher-Student Learning [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4472

Deep Signal Recovery With One-Bit Quantization

Paper Details

Authors:
Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar
Submitted On:
10 May 2019 - 6:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019.pdf

(50)

Subscribe

[1] Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar, "Deep Signal Recovery With One-Bit Quantization", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4422. Accessed: Dec. 13, 2019.
@article{4422-19,
url = {http://sigport.org/4422},
author = {Shahin Khobahi; Naveed Naimipour; Mojtaba Soltanalian; Yonina C. Eldar },
publisher = {IEEE SigPort},
title = {Deep Signal Recovery With One-Bit Quantization},
year = {2019} }
TY - EJOUR
T1 - Deep Signal Recovery With One-Bit Quantization
AU - Shahin Khobahi; Naveed Naimipour; Mojtaba Soltanalian; Yonina C. Eldar
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4422
ER -
Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar. (2019). Deep Signal Recovery With One-Bit Quantization. IEEE SigPort. http://sigport.org/4422
Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar, 2019. Deep Signal Recovery With One-Bit Quantization. Available at: http://sigport.org/4422.
Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar. (2019). "Deep Signal Recovery With One-Bit Quantization." Web.
1. Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar. Deep Signal Recovery With One-Bit Quantization [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4422

Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm


Tensor decomposition is a powerful tool for analyzing multiway data. Nowadays, with the fast development of multisensor technology, more and more data appear in higher-order (order >= 4) and nonnegative form. However, the decomposition of higher-order nonnegative tensor suffers from poor convergence and low speed. In this study, we propose a new nonnegative CANDECOM/PARAFAC (NCP) model using proximal algorithm. The block principal pivoting method in alternating nonnegative least squares (ANLS) framework is employed to minimize the objective function.

Paper Details

Authors:
Deqing Wang, Fengyu Cong, Tapani Ristaniemi
Submitted On:
10 May 2019 - 5:09pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

Wang_et_al_Poster_NCP_ICASSP2019.pdf

(49)

Subscribe

[1] Deqing Wang, Fengyu Cong, Tapani Ristaniemi, "Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4408. Accessed: Dec. 13, 2019.
@article{4408-19,
url = {http://sigport.org/4408},
author = {Deqing Wang; Fengyu Cong; Tapani Ristaniemi },
publisher = {IEEE SigPort},
title = {Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm},
year = {2019} }
TY - EJOUR
T1 - Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm
AU - Deqing Wang; Fengyu Cong; Tapani Ristaniemi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4408
ER -
Deqing Wang, Fengyu Cong, Tapani Ristaniemi. (2019). Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm. IEEE SigPort. http://sigport.org/4408
Deqing Wang, Fengyu Cong, Tapani Ristaniemi, 2019. Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm. Available at: http://sigport.org/4408.
Deqing Wang, Fengyu Cong, Tapani Ristaniemi. (2019). "Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm." Web.
1. Deqing Wang, Fengyu Cong, Tapani Ristaniemi. Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4408

DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES

Paper Details

Authors:
Or Yair, Danny Eytan, Ronen Talmon
Submitted On:
10 May 2019 - 2:37pm
Short Link:
Type:
Event:
Paper Code:

Document Files

icassp19poster.pdf

(30)

Subscribe

[1] Or Yair, Danny Eytan, Ronen Talmon, " DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4389. Accessed: Dec. 13, 2019.
@article{4389-19,
url = {http://sigport.org/4389},
author = {Or Yair; Danny Eytan; Ronen Talmon },
publisher = {IEEE SigPort},
title = { DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES},
year = {2019} }
TY - EJOUR
T1 - DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES
AU - Or Yair; Danny Eytan; Ronen Talmon
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4389
ER -
Or Yair, Danny Eytan, Ronen Talmon. (2019). DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES. IEEE SigPort. http://sigport.org/4389
Or Yair, Danny Eytan, Ronen Talmon, 2019. DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES. Available at: http://sigport.org/4389.
Or Yair, Danny Eytan, Ronen Talmon. (2019). " DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES." Web.
1. Or Yair, Danny Eytan, Ronen Talmon. DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4389

DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES

Paper Details

Authors:
Gal Maman, Or Yair, Danny Eytan, Ronen Talmon
Submitted On:
10 May 2019 - 2:37pm
Short Link:
Type:

Document Files

icassp19poster.pdf

(30)

Subscribe

[1] Gal Maman, Or Yair, Danny Eytan, Ronen Talmon, " DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4387. Accessed: Dec. 13, 2019.
@article{4387-19,
url = {http://sigport.org/4387},
author = {Gal Maman; Or Yair; Danny Eytan; Ronen Talmon },
publisher = {IEEE SigPort},
title = { DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES},
year = {2019} }
TY - EJOUR
T1 - DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES
AU - Gal Maman; Or Yair; Danny Eytan; Ronen Talmon
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4387
ER -
Gal Maman, Or Yair, Danny Eytan, Ronen Talmon. (2019). DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES. IEEE SigPort. http://sigport.org/4387
Gal Maman, Or Yair, Danny Eytan, Ronen Talmon, 2019. DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES. Available at: http://sigport.org/4387.
Gal Maman, Or Yair, Danny Eytan, Ronen Talmon. (2019). " DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES." Web.
1. Gal Maman, Or Yair, Danny Eytan, Ronen Talmon. DOMAIN ADAPTATION USING RIEMANNIAN GEOMETRY OF SPD MATRICES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4387

Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning

Paper Details

Authors:
Submitted On:
10 May 2019 - 1:06pm
Short Link:
Type:
Event:

Document Files

EMCN.pdf

(36)

Subscribe

[1] , "Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4374. Accessed: Dec. 13, 2019.
@article{4374-19,
url = {http://sigport.org/4374},
author = { },
publisher = {IEEE SigPort},
title = {Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning},
year = {2019} }
TY - EJOUR
T1 - Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4374
ER -
. (2019). Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning. IEEE SigPort. http://sigport.org/4374
, 2019. Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning. Available at: http://sigport.org/4374.
. (2019). "Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning." Web.
1. . Efficient Multi-agent Cooperative Navigation in Unknown Environments with Interlaced Deep Reinforcement Learning [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4374

Prediction of multi-target dynamics using discrete descriptors: An interactive approach


We propose a probabilistic method to track and interpret interactions of moving objects. The proposed method is based on the analysis of location data from different moving objects that modify their dynamics according to rules of interactions, namely attractive and repulsive forces governing moving objects in a scene. Our method uses a Bayesian structure to identify key elements of the interplay rules and facilitates the prediction of objects' dynamics as the interacting system.

Paper Details

Authors:
M. Baydoun, D. Campo, D. Kanapram, L. Marcenaro, C. Regazzoni
Submitted On:
10 May 2019 - 12:18pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

ICASSP2019Poster.pdf

(26)

Subscribe

[1] M. Baydoun, D. Campo, D. Kanapram, L. Marcenaro, C. Regazzoni , "Prediction of multi-target dynamics using discrete descriptors: An interactive approach", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4369. Accessed: Dec. 13, 2019.
@article{4369-19,
url = {http://sigport.org/4369},
author = {M. Baydoun; D. Campo; D. Kanapram; L. Marcenaro; C. Regazzoni },
publisher = {IEEE SigPort},
title = {Prediction of multi-target dynamics using discrete descriptors: An interactive approach},
year = {2019} }
TY - EJOUR
T1 - Prediction of multi-target dynamics using discrete descriptors: An interactive approach
AU - M. Baydoun; D. Campo; D. Kanapram; L. Marcenaro; C. Regazzoni
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4369
ER -
M. Baydoun, D. Campo, D. Kanapram, L. Marcenaro, C. Regazzoni . (2019). Prediction of multi-target dynamics using discrete descriptors: An interactive approach. IEEE SigPort. http://sigport.org/4369
M. Baydoun, D. Campo, D. Kanapram, L. Marcenaro, C. Regazzoni , 2019. Prediction of multi-target dynamics using discrete descriptors: An interactive approach. Available at: http://sigport.org/4369.
M. Baydoun, D. Campo, D. Kanapram, L. Marcenaro, C. Regazzoni . (2019). "Prediction of multi-target dynamics using discrete descriptors: An interactive approach." Web.
1. M. Baydoun, D. Campo, D. Kanapram, L. Marcenaro, C. Regazzoni . Prediction of multi-target dynamics using discrete descriptors: An interactive approach [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4369

Pages