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

Speech Enhancement (SPE-ENHA)

Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor

Paper Details

Authors:
Jun Du, Ian McLoughlin, Yong Xu, Feng Ma, Haikun Wang
Submitted On:
15 October 2016 - 1:32am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ISCSLP2016--Zhipeng_Xie_LDVs.pptx

(243 downloads)

ISCSLP2016--Zhipeng_Xie_LDVs.pdf

(253 downloads)

Subscribe

[1] Jun Du, Ian McLoughlin, Yong Xu, Feng Ma, Haikun Wang, "Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1194. Accessed: Aug. 18, 2018.
@article{1194-16,
url = {http://sigport.org/1194},
author = {Jun Du; Ian McLoughlin; Yong Xu; Feng Ma; Haikun Wang },
publisher = {IEEE SigPort},
title = {Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor},
year = {2016} }
TY - EJOUR
T1 - Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor
AU - Jun Du; Ian McLoughlin; Yong Xu; Feng Ma; Haikun Wang
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1194
ER -
Jun Du, Ian McLoughlin, Yong Xu, Feng Ma, Haikun Wang. (2016). Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor. IEEE SigPort. http://sigport.org/1194
Jun Du, Ian McLoughlin, Yong Xu, Feng Ma, Haikun Wang, 2016. Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor. Available at: http://sigport.org/1194.
Jun Du, Ian McLoughlin, Yong Xu, Feng Ma, Haikun Wang. (2016). "Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor." Web.
1. Jun Du, Ian McLoughlin, Yong Xu, Feng Ma, Haikun Wang. Deep Neural Network for Robust Speech Recognition With Auxiliary Features From Laser-Doppler Vibrometer Sensor [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1194

Speech Enhancement Based on Nonparametric Factor Analysis

Paper Details

Authors:
Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng
Submitted On:
14 October 2016 - 3:02am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

98-Speech Enhancement Based on Nonparametric Factor Analysis

(212 downloads)

Subscribe

[1] Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng, "Speech Enhancement Based on Nonparametric Factor Analysis", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1182. Accessed: Aug. 18, 2018.
@article{1182-16,
url = {http://sigport.org/1182},
author = {Lin Li; Jiawen Wu; Xinghao Ding; Qingyang Hong; Delu Zeng },
publisher = {IEEE SigPort},
title = {Speech Enhancement Based on Nonparametric Factor Analysis},
year = {2016} }
TY - EJOUR
T1 - Speech Enhancement Based on Nonparametric Factor Analysis
AU - Lin Li; Jiawen Wu; Xinghao Ding; Qingyang Hong; Delu Zeng
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1182
ER -
Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng. (2016). Speech Enhancement Based on Nonparametric Factor Analysis. IEEE SigPort. http://sigport.org/1182
Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng, 2016. Speech Enhancement Based on Nonparametric Factor Analysis. Available at: http://sigport.org/1182.
Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng. (2016). "Speech Enhancement Based on Nonparametric Factor Analysis." Web.
1. Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng. Speech Enhancement Based on Nonparametric Factor Analysis [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1182

Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability

Paper Details

Authors:
Submitted On:
22 March 2016 - 1:56am
Short Link:
Type:
Event:

Document Files

poster.pdf

(437 downloads)

Subscribe

[1] , "Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/952. Accessed: Aug. 18, 2018.
@article{952-16,
url = {http://sigport.org/952},
author = { },
publisher = {IEEE SigPort},
title = {Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability},
year = {2016} }
TY - EJOUR
T1 - Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/952
ER -
. (2016). Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability. IEEE SigPort. http://sigport.org/952
, 2016. Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability. Available at: http://sigport.org/952.
. (2016). "Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability." Web.
1. . Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probability [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/952

System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding


The ITU-T Recommendation G.722 about subband adaptive differential pulse code modulation (SB-ADPCM) is the mandatory wideband speech codec in the new generation digital enhanced cordless telephony (NG-DECT). Although in ADPCM the difference signal instead of the original signal is quantized and adaptive prediction is employed, redundancy is yet observed within the quantized samples. In this paper we apply a soft-decision speech decoding technique which exploits this redundancy in terms of a priori knowledge and the channel reliability information to NG-DECT.

poster.pdf

PDF icon poster.pdf (591 downloads)

Paper Details

Authors:
Sai Han, Angel M. Gomez, José Luis Pérez-Córdoba, Tim Fingscheidt
Submitted On:
19 March 2016 - 8:58am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

poster.pdf

(591 downloads)

Subscribe

[1] Sai Han, Angel M. Gomez, José Luis Pérez-Córdoba, Tim Fingscheidt, "System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/808. Accessed: Aug. 18, 2018.
@article{808-16,
url = {http://sigport.org/808},
author = {Sai Han; Angel M. Gomez; José Luis Pérez-Córdoba; Tim Fingscheidt },
publisher = {IEEE SigPort},
title = {System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding},
year = {2016} }
TY - EJOUR
T1 - System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding
AU - Sai Han; Angel M. Gomez; José Luis Pérez-Córdoba; Tim Fingscheidt
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/808
ER -
Sai Han, Angel M. Gomez, José Luis Pérez-Córdoba, Tim Fingscheidt. (2016). System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding. IEEE SigPort. http://sigport.org/808
Sai Han, Angel M. Gomez, José Luis Pérez-Córdoba, Tim Fingscheidt, 2016. System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding. Available at: http://sigport.org/808.
Sai Han, Angel M. Gomez, José Luis Pérez-Córdoba, Tim Fingscheidt. (2016). "System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding." Web.
1. Sai Han, Angel M. Gomez, José Luis Pérez-Córdoba, Tim Fingscheidt. System-Compatible Robustness Improvement for New Generation DECT Decoders by G.722 Soft-Decision Decoding [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/808

Sparse Reconstruction of Quantized Speech Signals


We propose sparse reconstruction techniques to improve the quality and / or reduce the bit-rate of standard speech coders. To that end, we assume signal sparsity in some transform domain and formulate the problem of reconstructing the original signal in terms of constrained l1-norm minimization. We use modern primal-dual methods in order to solve the resulting non-smooth convex optimization problem. Experiments show that with the proposed sparse reconstruction method the instrumentally predicted speech quality can be largely improved.

Paper Details

Authors:
Christoph Brauer, Timo Gerkmann, Dirk Lorenz
Submitted On:
17 March 2016 - 12:42pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp_poster_brauer.pdf

(352 downloads)

Subscribe

[1] Christoph Brauer, Timo Gerkmann, Dirk Lorenz, "Sparse Reconstruction of Quantized Speech Signals", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/744. Accessed: Aug. 18, 2018.
@article{744-16,
url = {http://sigport.org/744},
author = {Christoph Brauer; Timo Gerkmann; Dirk Lorenz },
publisher = {IEEE SigPort},
title = {Sparse Reconstruction of Quantized Speech Signals},
year = {2016} }
TY - EJOUR
T1 - Sparse Reconstruction of Quantized Speech Signals
AU - Christoph Brauer; Timo Gerkmann; Dirk Lorenz
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/744
ER -
Christoph Brauer, Timo Gerkmann, Dirk Lorenz. (2016). Sparse Reconstruction of Quantized Speech Signals. IEEE SigPort. http://sigport.org/744
Christoph Brauer, Timo Gerkmann, Dirk Lorenz, 2016. Sparse Reconstruction of Quantized Speech Signals. Available at: http://sigport.org/744.
Christoph Brauer, Timo Gerkmann, Dirk Lorenz. (2016). "Sparse Reconstruction of Quantized Speech Signals." Web.
1. Christoph Brauer, Timo Gerkmann, Dirk Lorenz. Sparse Reconstruction of Quantized Speech Signals [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/744

Multiplicative Update of AR gains in Codebook-driven Speech Enhancement

Paper Details

Authors:
Qi He,Changchun Bao,Feng Bao
Submitted On:
16 March 2016 - 12:13am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Multiplicative Update of AR Gains in Codebook-driven Speech Enhancement(ICASSP2016-Qi He).ppt

(0)

Subscribe

[1] Qi He,Changchun Bao,Feng Bao, "Multiplicative Update of AR gains in Codebook-driven Speech Enhancement ", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/664. Accessed: Aug. 18, 2018.
@article{664-16,
url = {http://sigport.org/664},
author = {Qi He;Changchun Bao;Feng Bao },
publisher = {IEEE SigPort},
title = {Multiplicative Update of AR gains in Codebook-driven Speech Enhancement },
year = {2016} }
TY - EJOUR
T1 - Multiplicative Update of AR gains in Codebook-driven Speech Enhancement
AU - Qi He;Changchun Bao;Feng Bao
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/664
ER -
Qi He,Changchun Bao,Feng Bao. (2016). Multiplicative Update of AR gains in Codebook-driven Speech Enhancement . IEEE SigPort. http://sigport.org/664
Qi He,Changchun Bao,Feng Bao, 2016. Multiplicative Update of AR gains in Codebook-driven Speech Enhancement . Available at: http://sigport.org/664.
Qi He,Changchun Bao,Feng Bao. (2016). "Multiplicative Update of AR gains in Codebook-driven Speech Enhancement ." Web.
1. Qi He,Changchun Bao,Feng Bao. Multiplicative Update of AR gains in Codebook-driven Speech Enhancement [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/664

USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION

Paper Details

Authors:
Yingxue Wang, Shenghui Zhao, Dan Qu, Jingming Kuang
Submitted On:
13 March 2016 - 4:57pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

poster_icassp2016.pdf

(380 downloads)

Subscribe

[1] Yingxue Wang, Shenghui Zhao, Dan Qu, Jingming Kuang, "USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/657. Accessed: Aug. 18, 2018.
@article{657-16,
url = {http://sigport.org/657},
author = {Yingxue Wang; Shenghui Zhao; Dan Qu; Jingming Kuang },
publisher = {IEEE SigPort},
title = {USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION},
year = {2016} }
TY - EJOUR
T1 - USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION
AU - Yingxue Wang; Shenghui Zhao; Dan Qu; Jingming Kuang
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/657
ER -
Yingxue Wang, Shenghui Zhao, Dan Qu, Jingming Kuang. (2016). USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION. IEEE SigPort. http://sigport.org/657
Yingxue Wang, Shenghui Zhao, Dan Qu, Jingming Kuang, 2016. USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION. Available at: http://sigport.org/657.
Yingxue Wang, Shenghui Zhao, Dan Qu, Jingming Kuang. (2016). "USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION." Web.
1. Yingxue Wang, Shenghui Zhao, Dan Qu, Jingming Kuang. USING CONDITIONAL RESTRICTED BOLTZMANN MACHINES FOR SPECTRAL ENVELOPE MODELING IN SPEECH BANDWIDTH EXTENSION [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/657

A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing

Paper Details

Authors:
Chetan Vahanesa, Issa M.S. Panahi
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

GlobalSIP_YU_RAO.pptx

(376 downloads)

Subscribe

[1] Chetan Vahanesa, Issa M.S. Panahi, "A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/457. Accessed: Aug. 18, 2018.
@article{457-15,
url = {http://sigport.org/457},
author = {Chetan Vahanesa; Issa M.S. Panahi },
publisher = {IEEE SigPort},
title = {A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing},
year = {2015} }
TY - EJOUR
T1 - A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing
AU - Chetan Vahanesa; Issa M.S. Panahi
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/457
ER -
Chetan Vahanesa, Issa M.S. Panahi. (2015). A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing. IEEE SigPort. http://sigport.org/457
Chetan Vahanesa, Issa M.S. Panahi, 2015. A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing. Available at: http://sigport.org/457.
Chetan Vahanesa, Issa M.S. Panahi. (2015). "A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing." Web.
1. Chetan Vahanesa, Issa M.S. Panahi. A two-stage data-driven single microphone speech enhancement with cepstral analysis pre-processing [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/457

Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction

Paper Details

Authors:
Vahid Montazeri, Yu Rao, Issa Panahi
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

GlobalSIP Presentation_Final_Chandan.pptx

(339 downloads)

Subscribe

[1] Vahid Montazeri, Yu Rao, Issa Panahi, "Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction ", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/432. Accessed: Aug. 18, 2018.
@article{432-15,
url = {http://sigport.org/432},
author = {Vahid Montazeri; Yu Rao; Issa Panahi },
publisher = {IEEE SigPort},
title = {Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction },
year = {2015} }
TY - EJOUR
T1 - Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction
AU - Vahid Montazeri; Yu Rao; Issa Panahi
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/432
ER -
Vahid Montazeri, Yu Rao, Issa Panahi. (2015). Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction . IEEE SigPort. http://sigport.org/432
Vahid Montazeri, Yu Rao, Issa Panahi, 2015. Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction . Available at: http://sigport.org/432.
Vahid Montazeri, Yu Rao, Issa Panahi. (2015). "Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction ." Web.
1. Vahid Montazeri, Yu Rao, Issa Panahi. Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/432

Guided Signal Reconstruction with Application to Image Magnification


Reconstruction Set

We propose signal reconstruction algorithms which utilize a guiding subspace that represents desired properties of reconstructed signals. Optimal reconstructed signals are shown to belong to a convex bounded set, called the ``reconstruction'' set. Iterative reconstruction algorithms, based on conjugate gradient methods, are developed to approximate optimal reconstructions with low memory and computational costs. Effectiveness of the proposed method is demonstrated with an application to image magnification.

Paper Details

Authors:
Akshay Gadde, Hassan Mansour, Dong Tian
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

globalsip-15-slides-v2.pdf

(413 downloads)

Subscribe

[1] Akshay Gadde, Hassan Mansour, Dong Tian, "Guided Signal Reconstruction with Application to Image Magnification", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/384. Accessed: Aug. 18, 2018.
@article{384-15,
url = {http://sigport.org/384},
author = {Akshay Gadde; Hassan Mansour; Dong Tian },
publisher = {IEEE SigPort},
title = {Guided Signal Reconstruction with Application to Image Magnification},
year = {2015} }
TY - EJOUR
T1 - Guided Signal Reconstruction with Application to Image Magnification
AU - Akshay Gadde; Hassan Mansour; Dong Tian
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/384
ER -
Akshay Gadde, Hassan Mansour, Dong Tian. (2015). Guided Signal Reconstruction with Application to Image Magnification. IEEE SigPort. http://sigport.org/384
Akshay Gadde, Hassan Mansour, Dong Tian, 2015. Guided Signal Reconstruction with Application to Image Magnification. Available at: http://sigport.org/384.
Akshay Gadde, Hassan Mansour, Dong Tian. (2015). "Guided Signal Reconstruction with Application to Image Magnification." Web.
1. Akshay Gadde, Hassan Mansour, Dong Tian. Guided Signal Reconstruction with Application to Image Magnification [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/384

Pages