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

Audio and Acoustic Signal Processing

REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE


Wave-based acoustic simulation methods are studied actively for predicting acoustical phenomena. Finite-difference timedomain (FDTD) method is one of the most popular methods owing to its straightforwardness of calculating an impulse response. In an FDTD simulation, an omnidirectional sound source is usually adopted, which is not realistic because the real sound sources often have specific directivities. However, there is very little research on imposing a directional sound source into FDTD methods.

Paper Details

Authors:
Daiki Takeuchi, Kohei Yatabe, Yasuhiro Oikawa
Submitted On:
17 April 2018 - 10:59am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018Poster.pdf

(70 downloads)

Subscribe

[1] Daiki Takeuchi, Kohei Yatabe, Yasuhiro Oikawa, "REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2936. Accessed: Sep. 22, 2018.
@article{2936-18,
url = {http://sigport.org/2936},
author = {Daiki Takeuchi; Kohei Yatabe; Yasuhiro Oikawa },
publisher = {IEEE SigPort},
title = {REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE},
year = {2018} }
TY - EJOUR
T1 - REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE
AU - Daiki Takeuchi; Kohei Yatabe; Yasuhiro Oikawa
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2936
ER -
Daiki Takeuchi, Kohei Yatabe, Yasuhiro Oikawa. (2018). REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE. IEEE SigPort. http://sigport.org/2936
Daiki Takeuchi, Kohei Yatabe, Yasuhiro Oikawa, 2018. REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE. Available at: http://sigport.org/2936.
Daiki Takeuchi, Kohei Yatabe, Yasuhiro Oikawa. (2018). "REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE." Web.
1. Daiki Takeuchi, Kohei Yatabe, Yasuhiro Oikawa. REALIZING DIRECTIONAL SOUND SOURCE IN FDTD METHOD BY ESTIMATING INITIAL VALUE [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2936

Maximal Figure-of-Merit Embedding for Multi-label Audio Classification

Paper Details

Authors:
Ivan Kukanov, Ville Hautamaki, Kong Aik Lee
Submitted On:
19 April 2018 - 12:02pm
Short Link:
Type:
Event:

Document Files

Presentation.pdf

(611 downloads)

Keywords

Additional Categories

Subscribe

[1] Ivan Kukanov, Ville Hautamaki, Kong Aik Lee, "Maximal Figure-of-Merit Embedding for Multi-label Audio Classification", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2935. Accessed: Sep. 22, 2018.
@article{2935-18,
url = {http://sigport.org/2935},
author = {Ivan Kukanov; Ville Hautamaki; Kong Aik Lee },
publisher = {IEEE SigPort},
title = {Maximal Figure-of-Merit Embedding for Multi-label Audio Classification},
year = {2018} }
TY - EJOUR
T1 - Maximal Figure-of-Merit Embedding for Multi-label Audio Classification
AU - Ivan Kukanov; Ville Hautamaki; Kong Aik Lee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2935
ER -
Ivan Kukanov, Ville Hautamaki, Kong Aik Lee. (2018). Maximal Figure-of-Merit Embedding for Multi-label Audio Classification. IEEE SigPort. http://sigport.org/2935
Ivan Kukanov, Ville Hautamaki, Kong Aik Lee, 2018. Maximal Figure-of-Merit Embedding for Multi-label Audio Classification. Available at: http://sigport.org/2935.
Ivan Kukanov, Ville Hautamaki, Kong Aik Lee. (2018). "Maximal Figure-of-Merit Embedding for Multi-label Audio Classification." Web.
1. Ivan Kukanov, Ville Hautamaki, Kong Aik Lee. Maximal Figure-of-Merit Embedding for Multi-label Audio Classification [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2935

Time-Frequency Networks for Audio Super-Resolution


Audio super-resolution (a.k.a. bandwidth extension) is the challenging task of increasing the temporal resolution of audio signals. Recent deep networks approaches achieved promising results by modeling the task as a regression problem in either time or frequency domain. In this paper, we introduced Time-Frequency Network (TFNet), a deep network that utilizes supervision in both the time and frequency domain. We proposed a novel model architecture which allows the two domains to be jointly optimized.

Paper Details

Authors:
Yijia Xu, Minh N. Do, Mark Hasegawa-Johnson
Submitted On:
17 April 2018 - 12:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

audio_sr_poster.pdf

(140 downloads)

Subscribe

[1] Yijia Xu, Minh N. Do, Mark Hasegawa-Johnson, "Time-Frequency Networks for Audio Super-Resolution", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2928. Accessed: Sep. 22, 2018.
@article{2928-18,
url = {http://sigport.org/2928},
author = {Yijia Xu; Minh N. Do; Mark Hasegawa-Johnson },
publisher = {IEEE SigPort},
title = {Time-Frequency Networks for Audio Super-Resolution},
year = {2018} }
TY - EJOUR
T1 - Time-Frequency Networks for Audio Super-Resolution
AU - Yijia Xu; Minh N. Do; Mark Hasegawa-Johnson
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2928
ER -
Yijia Xu, Minh N. Do, Mark Hasegawa-Johnson. (2018). Time-Frequency Networks for Audio Super-Resolution. IEEE SigPort. http://sigport.org/2928
Yijia Xu, Minh N. Do, Mark Hasegawa-Johnson, 2018. Time-Frequency Networks for Audio Super-Resolution. Available at: http://sigport.org/2928.
Yijia Xu, Minh N. Do, Mark Hasegawa-Johnson. (2018). "Time-Frequency Networks for Audio Super-Resolution." Web.
1. Yijia Xu, Minh N. Do, Mark Hasegawa-Johnson. Time-Frequency Networks for Audio Super-Resolution [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2928

Deep Clustering with Gated Convolutional Networks

Paper Details

Authors:
Submitted On:
16 April 2018 - 8:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_ppt.pdf

(178 downloads)

Subscribe

[1] , "Deep Clustering with Gated Convolutional Networks", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2923. Accessed: Sep. 22, 2018.
@article{2923-18,
url = {http://sigport.org/2923},
author = { },
publisher = {IEEE SigPort},
title = {Deep Clustering with Gated Convolutional Networks},
year = {2018} }
TY - EJOUR
T1 - Deep Clustering with Gated Convolutional Networks
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2923
ER -
. (2018). Deep Clustering with Gated Convolutional Networks. IEEE SigPort. http://sigport.org/2923
, 2018. Deep Clustering with Gated Convolutional Networks. Available at: http://sigport.org/2923.
. (2018). "Deep Clustering with Gated Convolutional Networks." Web.
1. . Deep Clustering with Gated Convolutional Networks [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2923

EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION

Paper Details

Authors:
Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Jinyu Li, Michael L. Seltzer, Yifan Gong
Submitted On:
16 April 2018 - 6:07pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_icassp.pdf

(120 downloads)

Subscribe

[1] Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Jinyu Li, Michael L. Seltzer, Yifan Gong, "EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2919. Accessed: Sep. 22, 2018.
@article{2919-18,
url = {http://sigport.org/2919},
author = {Zhuo Chen; Takuya Yoshioka; Xiong Xiao; Jinyu Li; Michael L. Seltzer; Yifan Gong },
publisher = {IEEE SigPort},
title = {EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION},
year = {2018} }
TY - EJOUR
T1 - EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION
AU - Zhuo Chen; Takuya Yoshioka; Xiong Xiao; Jinyu Li; Michael L. Seltzer; Yifan Gong
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2919
ER -
Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Jinyu Li, Michael L. Seltzer, Yifan Gong. (2018). EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION. IEEE SigPort. http://sigport.org/2919
Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Jinyu Li, Michael L. Seltzer, Yifan Gong, 2018. EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION. Available at: http://sigport.org/2919.
Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Jinyu Li, Michael L. Seltzer, Yifan Gong. (2018). "EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION." Web.
1. Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Jinyu Li, Michael L. Seltzer, Yifan Gong. EFFICIENT INTEGRATION OF FIXED BEAMFORMERS AND SPEECH SEPARATION NETWORKS FOR MULTICHANNEL FAR-FIELD SPEECH SEPARATION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2919

AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM

Paper Details

Authors:
Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero
Submitted On:
16 April 2018 - 8:48am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP18_Janus_slides.pptx

(71 downloads)

Subscribe

[1] Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero, "AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2913. Accessed: Sep. 22, 2018.
@article{2913-18,
url = {http://sigport.org/2913},
author = {Gregory Sell; Kevin Duh; David Snyder; Dave Etter; Daniel Garcia-Romero },
publisher = {IEEE SigPort},
title = {AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM},
year = {2018} }
TY - EJOUR
T1 - AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM
AU - Gregory Sell; Kevin Duh; David Snyder; Dave Etter; Daniel Garcia-Romero
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2913
ER -
Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero. (2018). AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM. IEEE SigPort. http://sigport.org/2913
Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero, 2018. AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM. Available at: http://sigport.org/2913.
Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero. (2018). "AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM." Web.
1. Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero. AUDIO-VISUAL PERSON RECOGNITION IN MULTIMEDIA DATA FROM THE IARPA JANUS PROGRAM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2913

ImageFusion Using Belief Propagation

Paper Details

Authors:
Dave Bull
Submitted On:
15 April 2018 - 6:47pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster for ICASSP 2018

(41 downloads)

Subscribe

[1] Dave Bull, "ImageFusion Using Belief Propagation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2902. Accessed: Sep. 22, 2018.
@article{2902-18,
url = {http://sigport.org/2902},
author = {Dave Bull },
publisher = {IEEE SigPort},
title = {ImageFusion Using Belief Propagation},
year = {2018} }
TY - EJOUR
T1 - ImageFusion Using Belief Propagation
AU - Dave Bull
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2902
ER -
Dave Bull. (2018). ImageFusion Using Belief Propagation. IEEE SigPort. http://sigport.org/2902
Dave Bull, 2018. ImageFusion Using Belief Propagation. Available at: http://sigport.org/2902.
Dave Bull. (2018). "ImageFusion Using Belief Propagation." Web.
1. Dave Bull. ImageFusion Using Belief Propagation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2902

A Novel Thresholding Technique for the Denoising of Multicomponent Signals


This paper addresses the issues of the denoising and retrieval of the components of multicomponent signals from their short-time Fourier transform (STFT). After having recalled the hard-thresholding technique, in the STFT context, we develop a new thresholding technique by exploiting some limitations of the former. Numerical experiments illustrating the benefits of the proposed method to retrieve the modes of noisy multicomponent signals conclude the paper.

Paper Details

Authors:
Sylvain Meignen
Submitted On:
15 April 2018 - 8:50am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

presentation_cor_Sylvain.pdf

(48 downloads)

Subscribe

[1] Sylvain Meignen, "A Novel Thresholding Technique for the Denoising of Multicomponent Signals", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2893. Accessed: Sep. 22, 2018.
@article{2893-18,
url = {http://sigport.org/2893},
author = {Sylvain Meignen },
publisher = {IEEE SigPort},
title = {A Novel Thresholding Technique for the Denoising of Multicomponent Signals},
year = {2018} }
TY - EJOUR
T1 - A Novel Thresholding Technique for the Denoising of Multicomponent Signals
AU - Sylvain Meignen
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2893
ER -
Sylvain Meignen. (2018). A Novel Thresholding Technique for the Denoising of Multicomponent Signals. IEEE SigPort. http://sigport.org/2893
Sylvain Meignen, 2018. A Novel Thresholding Technique for the Denoising of Multicomponent Signals. Available at: http://sigport.org/2893.
Sylvain Meignen. (2018). "A Novel Thresholding Technique for the Denoising of Multicomponent Signals." Web.
1. Sylvain Meignen. A Novel Thresholding Technique for the Denoising of Multicomponent Signals [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2893

Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation

Paper Details

Authors:
Christopher Tegho, Pawel Budzianowski, Milica Gasic
Submitted On:
19 April 2018 - 12:50pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP Presentation (1).pdf

(76 downloads)

Keywords

Additional Categories

Subscribe

[1] Christopher Tegho, Pawel Budzianowski, Milica Gasic, "Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2891. Accessed: Sep. 22, 2018.
@article{2891-18,
url = {http://sigport.org/2891},
author = {Christopher Tegho; Pawel Budzianowski; Milica Gasic },
publisher = {IEEE SigPort},
title = {Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation},
year = {2018} }
TY - EJOUR
T1 - Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation
AU - Christopher Tegho; Pawel Budzianowski; Milica Gasic
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2891
ER -
Christopher Tegho, Pawel Budzianowski, Milica Gasic. (2018). Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation. IEEE SigPort. http://sigport.org/2891
Christopher Tegho, Pawel Budzianowski, Milica Gasic, 2018. Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation. Available at: http://sigport.org/2891.
Christopher Tegho, Pawel Budzianowski, Milica Gasic. (2018). "Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation." Web.
1. Christopher Tegho, Pawel Budzianowski, Milica Gasic. Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2891

SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS


Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. Some research works trying to modify the sentiment of the output sequences were reported. In this paper, we propose five models to scale or adjust the sentiment of the chatbot response: persona-based model, reinforcement learning, plug and play model, sentiment transformation network and cycleGAN, all based on the conventional seq2seq model.

lee.pdf

PDF icon lee.pdf (70 downloads)

Paper Details

Authors:
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee
Submitted On:
15 April 2018 - 4:05am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

lee.pdf

(70 downloads)

Keywords

Additional Categories

Subscribe

[1] Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee, "SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2887. Accessed: Sep. 22, 2018.
@article{2887-18,
url = {http://sigport.org/2887},
author = {Chih-Wei Lee; Yau-Shian Wang; Tsung-Yuan Hsu; Kuan-Yu Chen; Hung-Yi Lee; Lin-shan Lee },
publisher = {IEEE SigPort},
title = {SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS
AU - Chih-Wei Lee; Yau-Shian Wang; Tsung-Yuan Hsu; Kuan-Yu Chen; Hung-Yi Lee; Lin-shan Lee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2887
ER -
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. (2018). SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS. IEEE SigPort. http://sigport.org/2887
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee, 2018. SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS. Available at: http://sigport.org/2887.
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. (2018). "SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS." Web.
1. Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2887

Pages