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

Audio and Acoustic Signal Processing

UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION


The scarcity of emotional speech data is a bottleneck of developing automatic speech emotion recognition (ASER) systems. One way to alleviate this issue is to use unsupervised feature learning techniques to learn features from the widely available general speech and use these features to train emotion classifiers. These unsupervised methods, such as denoising autoencoder (DAE), variational autoencoder (VAE), adversarial autoencoder (AAE) and adversarial variational Bayes (AVB), can capture the intrinsic structure of the data distribution in the learned feature representation.

Paper Details

Authors:
Sefik Emre Eskimez, Zhiyao Duan, Wendi Heinzelman
Submitted On:
19 April 2018 - 4:01pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp-2018-poster.pdf

(89 downloads)

Keywords

Additional Categories

Subscribe

[1] Sefik Emre Eskimez, Zhiyao Duan, Wendi Heinzelman, "UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3017. Accessed: Sep. 22, 2018.
@article{3017-18,
url = {http://sigport.org/3017},
author = {Sefik Emre Eskimez; Zhiyao Duan; Wendi Heinzelman },
publisher = {IEEE SigPort},
title = {UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION},
year = {2018} }
TY - EJOUR
T1 - UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION
AU - Sefik Emre Eskimez; Zhiyao Duan; Wendi Heinzelman
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3017
ER -
Sefik Emre Eskimez, Zhiyao Duan, Wendi Heinzelman. (2018). UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION. IEEE SigPort. http://sigport.org/3017
Sefik Emre Eskimez, Zhiyao Duan, Wendi Heinzelman, 2018. UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION. Available at: http://sigport.org/3017.
Sefik Emre Eskimez, Zhiyao Duan, Wendi Heinzelman. (2018). "UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION." Web.
1. Sefik Emre Eskimez, Zhiyao Duan, Wendi Heinzelman. UNSUPERVISED LEARNING APPROACH TO FEATURE ANALYSIS FOR AUTOMATIC SPEECH EMOTION RECOGNITION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3017

Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio

Paper Details

Authors:
Submitted On:
19 April 2018 - 3:22pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

presentation_final.pdf

(260 downloads)

Subscribe

[1] , "Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3010. Accessed: Sep. 22, 2018.
@article{3010-18,
url = {http://sigport.org/3010},
author = { },
publisher = {IEEE SigPort},
title = {Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio},
year = {2018} }
TY - EJOUR
T1 - Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3010
ER -
. (2018). Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio. IEEE SigPort. http://sigport.org/3010
, 2018. Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio. Available at: http://sigport.org/3010.
. (2018). "Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio." Web.
1. . Learning-Based Acoustic Source-Microphone Distance Estimation using the Coherent-to-Diffuse Power Ratio [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3010

Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines

Paper Details

Authors:
Abelino Jimenez, Benjamin Elizalde, Bhiksha Raj
Submitted On:
19 April 2018 - 2:56pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp.pptx

(121 downloads)

Subscribe

[1] Abelino Jimenez, Benjamin Elizalde, Bhiksha Raj, "Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3006. Accessed: Sep. 22, 2018.
@article{3006-18,
url = {http://sigport.org/3006},
author = {Abelino Jimenez; Benjamin Elizalde; Bhiksha Raj },
publisher = {IEEE SigPort},
title = {Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines},
year = {2018} }
TY - EJOUR
T1 - Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines
AU - Abelino Jimenez; Benjamin Elizalde; Bhiksha Raj
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3006
ER -
Abelino Jimenez, Benjamin Elizalde, Bhiksha Raj. (2018). Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines. IEEE SigPort. http://sigport.org/3006
Abelino Jimenez, Benjamin Elizalde, Bhiksha Raj, 2018. Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines. Available at: http://sigport.org/3006.
Abelino Jimenez, Benjamin Elizalde, Bhiksha Raj. (2018). "Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines." Web.
1. Abelino Jimenez, Benjamin Elizalde, Bhiksha Raj. Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3006

Distributed Maximum Likelihood using Dynamic Average Consensus


This paper presents the formulation and analysis of a novel distributed maximum likelihood algorithm that utilizes a first-order optimization scheme. The proposed approach utilizes a static average consensus algorithm to reach agreement on the initial condition to the iterative optimization scheme and a dynamic average consensus algorithm to reach agreement on the gradient direction. The current distributed algorithm is guaranteed to exponentially recover the performance of the centralized algorithm.

Paper Details

Authors:
Submitted On:
19 April 2018 - 2:52pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

George_ICASSP_v1.pdf

(57 downloads)

Keywords

Additional Categories

Subscribe

[1] , "Distributed Maximum Likelihood using Dynamic Average Consensus", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3003. Accessed: Sep. 22, 2018.
@article{3003-18,
url = {http://sigport.org/3003},
author = { },
publisher = {IEEE SigPort},
title = {Distributed Maximum Likelihood using Dynamic Average Consensus},
year = {2018} }
TY - EJOUR
T1 - Distributed Maximum Likelihood using Dynamic Average Consensus
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3003
ER -
. (2018). Distributed Maximum Likelihood using Dynamic Average Consensus. IEEE SigPort. http://sigport.org/3003
, 2018. Distributed Maximum Likelihood using Dynamic Average Consensus. Available at: http://sigport.org/3003.
. (2018). "Distributed Maximum Likelihood using Dynamic Average Consensus." Web.
1. . Distributed Maximum Likelihood using Dynamic Average Consensus [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3003

END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING

Paper Details

Authors:
Lei Chen, Jidong Tao, Shabnam Ghaffarzadegan, Yao Qian
Submitted On:
19 April 2018 - 2:45pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

icassp2018_final.pdf

(57 downloads)

Keywords

Additional Categories

Subscribe

[1] Lei Chen, Jidong Tao, Shabnam Ghaffarzadegan, Yao Qian, "END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2999. Accessed: Sep. 22, 2018.
@article{2999-18,
url = {http://sigport.org/2999},
author = {Lei Chen; Jidong Tao; Shabnam Ghaffarzadegan; Yao Qian },
publisher = {IEEE SigPort},
title = {END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING},
year = {2018} }
TY - EJOUR
T1 - END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING
AU - Lei Chen; Jidong Tao; Shabnam Ghaffarzadegan; Yao Qian
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2999
ER -
Lei Chen, Jidong Tao, Shabnam Ghaffarzadegan, Yao Qian. (2018). END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING. IEEE SigPort. http://sigport.org/2999
Lei Chen, Jidong Tao, Shabnam Ghaffarzadegan, Yao Qian, 2018. END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING. Available at: http://sigport.org/2999.
Lei Chen, Jidong Tao, Shabnam Ghaffarzadegan, Yao Qian. (2018). "END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING." Web.
1. Lei Chen, Jidong Tao, Shabnam Ghaffarzadegan, Yao Qian. END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2999

MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION

Paper Details

Authors:
Vahid Khorasani Ghassab, Arash Mohammadi, Seyed Farokh Atashzar, Rajni V. Patel
Submitted On:
19 April 2018 - 2:34pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_v1.pdf

(69 downloads)

Subscribe

[1] Vahid Khorasani Ghassab, Arash Mohammadi, Seyed Farokh Atashzar, Rajni V. Patel, "MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2993. Accessed: Sep. 22, 2018.
@article{2993-18,
url = {http://sigport.org/2993},
author = {Vahid Khorasani Ghassab; Arash Mohammadi; Seyed Farokh Atashzar; Rajni V. Patel },
publisher = {IEEE SigPort},
title = {MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION},
year = {2018} }
TY - EJOUR
T1 - MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION
AU - Vahid Khorasani Ghassab; Arash Mohammadi; Seyed Farokh Atashzar; Rajni V. Patel
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2993
ER -
Vahid Khorasani Ghassab, Arash Mohammadi, Seyed Farokh Atashzar, Rajni V. Patel. (2018). MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION. IEEE SigPort. http://sigport.org/2993
Vahid Khorasani Ghassab, Arash Mohammadi, Seyed Farokh Atashzar, Rajni V. Patel, 2018. MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION. Available at: http://sigport.org/2993.
Vahid Khorasani Ghassab, Arash Mohammadi, Seyed Farokh Atashzar, Rajni V. Patel. (2018). "MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION." Web.
1. Vahid Khorasani Ghassab, Arash Mohammadi, Seyed Farokh Atashzar, Rajni V. Patel. MULTIPLE-MODEL AND REDUCED-ORDER KALMAN FILTERING FOR PATHOLOGICAL HAND TREMOR EXTRACTION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2993

Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition

Paper Details

Authors:
Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu
Submitted On:
19 April 2018 - 4:56am
Short Link:
Type:
Paper Code:

Document Files

ICASSP2018-Peng.pdf

(105 downloads)

Subscribe

[1] Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu, "Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2980. Accessed: Sep. 22, 2018.
@article{2980-18,
url = {http://sigport.org/2980},
author = {Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu },
publisher = {IEEE SigPort},
title = {Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition},
year = {2018} }
TY - EJOUR
T1 - Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition
AU - Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2980
ER -
Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu. (2018). Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition. IEEE SigPort. http://sigport.org/2980
Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu, 2018. Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition. Available at: http://sigport.org/2980.
Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu. (2018). "Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition." Web.
1. Peng Song, Wenming Zheng, Shifeng Ou,Yun Jin, Wenming Ma, Yanwei Yu. Joint Transfer Subspace Learning and Feature Selection for Cross-corpus Speech Emotion Recognition [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2980

WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION

Paper Details

Authors:
Timo Gerkmann, Alfred Mertins
Submitted On:
17 April 2018 - 3:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_Poster.pdf

(145 downloads)

Subscribe

[1] Timo Gerkmann, Alfred Mertins, "WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2944. Accessed: Sep. 22, 2018.
@article{2944-18,
url = {http://sigport.org/2944},
author = {Timo Gerkmann; Alfred Mertins },
publisher = {IEEE SigPort},
title = {WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION},
year = {2018} }
TY - EJOUR
T1 - WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION
AU - Timo Gerkmann; Alfred Mertins
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2944
ER -
Timo Gerkmann, Alfred Mertins. (2018). WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION. IEEE SigPort. http://sigport.org/2944
Timo Gerkmann, Alfred Mertins, 2018. WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION. Available at: http://sigport.org/2944.
Timo Gerkmann, Alfred Mertins. (2018). "WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION." Web.
1. Timo Gerkmann, Alfred Mertins. WEIGHTED AND MULTI-TASK LOSS FOR RARE AUDIO EVENT DETECTION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2944

ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS

Paper Details

Authors:
Philipp Koch, Ian McLoughlin, Alfred Mertins
Submitted On:
17 April 2018 - 3:51pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2018.pdf

(42 downloads)

Subscribe

[1] Philipp Koch, Ian McLoughlin, Alfred Mertins, "ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2943. Accessed: Sep. 22, 2018.
@article{2943-18,
url = {http://sigport.org/2943},
author = {Philipp Koch; Ian McLoughlin; Alfred Mertins },
publisher = {IEEE SigPort},
title = {ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS},
year = {2018} }
TY - EJOUR
T1 - ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS
AU - Philipp Koch; Ian McLoughlin; Alfred Mertins
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2943
ER -
Philipp Koch, Ian McLoughlin, Alfred Mertins. (2018). ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS. IEEE SigPort. http://sigport.org/2943
Philipp Koch, Ian McLoughlin, Alfred Mertins, 2018. ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS. Available at: http://sigport.org/2943.
Philipp Koch, Ian McLoughlin, Alfred Mertins. (2018). "ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS." Web.
1. Philipp Koch, Ian McLoughlin, Alfred Mertins. ENABLING EARLY AUDIO EVENT DETECTION WITH NEURAL NETWORKS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2943

Generative Adversarial Source Separation


pres.pdf

PDF icon pres.pdf (69 downloads)

Paper Details

Authors:
Submitted On:
17 April 2018 - 1:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

pres.pdf

(69 downloads)

Subscribe

[1] , "Generative Adversarial Source Separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2937. Accessed: Sep. 22, 2018.
@article{2937-18,
url = {http://sigport.org/2937},
author = { },
publisher = {IEEE SigPort},
title = {Generative Adversarial Source Separation},
year = {2018} }
TY - EJOUR
T1 - Generative Adversarial Source Separation
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2937
ER -
. (2018). Generative Adversarial Source Separation. IEEE SigPort. http://sigport.org/2937
, 2018. Generative Adversarial Source Separation. Available at: http://sigport.org/2937.
. (2018). "Generative Adversarial Source Separation." Web.
1. . Generative Adversarial Source Separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2937

Pages