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

Audio and Acoustic Signal Processing

Fast and Easy Crowdsourced Perceptual Audio Evaluation


Crowdsourced Audio Quality Evaluation

Automated objective methods of audio evaluation are fast, cheap, and require little effort by the investigator. However, objective evaluation methods do not exist for the output of all audio processing algorithms, often have output that correlates poorly with human quality assessments, and require ground truth data in their calculation. Subjective human ratings of audio quality are the gold standard for many tasks, but are expensive, slow, and require a great deal of effort to recruit subjects and run listening tests.

Paper Details

Authors:
Mark Cartwright, Bryan Pardo, Gautham J. Mysore, Matt Hoffman
Submitted On:
16 March 2016 - 9:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp_poster_print.pdf

(142 downloads)

Keywords

Additional Categories

Subscribe

[1] Mark Cartwright, Bryan Pardo, Gautham J. Mysore, Matt Hoffman, "Fast and Easy Crowdsourced Perceptual Audio Evaluation", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/727. Accessed: Jun. 29, 2017.
@article{727-16,
url = {http://sigport.org/727},
author = {Mark Cartwright; Bryan Pardo; Gautham J. Mysore; Matt Hoffman },
publisher = {IEEE SigPort},
title = {Fast and Easy Crowdsourced Perceptual Audio Evaluation},
year = {2016} }
TY - EJOUR
T1 - Fast and Easy Crowdsourced Perceptual Audio Evaluation
AU - Mark Cartwright; Bryan Pardo; Gautham J. Mysore; Matt Hoffman
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/727
ER -
Mark Cartwright, Bryan Pardo, Gautham J. Mysore, Matt Hoffman. (2016). Fast and Easy Crowdsourced Perceptual Audio Evaluation. IEEE SigPort. http://sigport.org/727
Mark Cartwright, Bryan Pardo, Gautham J. Mysore, Matt Hoffman, 2016. Fast and Easy Crowdsourced Perceptual Audio Evaluation. Available at: http://sigport.org/727.
Mark Cartwright, Bryan Pardo, Gautham J. Mysore, Matt Hoffman. (2016). "Fast and Easy Crowdsourced Perceptual Audio Evaluation." Web.
1. Mark Cartwright, Bryan Pardo, Gautham J. Mysore, Matt Hoffman. Fast and Easy Crowdsourced Perceptual Audio Evaluation [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/727

GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES

Paper Details

Authors:
Xiaojun Qiu, Eva Cheng, Ian Burnett
Submitted On:
15 March 2016 - 11:47pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES_POSTER.pdf

(139 downloads)

Keywords

Subscribe

[1] Xiaojun Qiu, Eva Cheng, Ian Burnett, "GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES ", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/702. Accessed: Jun. 29, 2017.
@article{702-16,
url = {http://sigport.org/702},
author = {Xiaojun Qiu; Eva Cheng; Ian Burnett },
publisher = {IEEE SigPort},
title = {GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES },
year = {2016} }
TY - EJOUR
T1 - GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES
AU - Xiaojun Qiu; Eva Cheng; Ian Burnett
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/702
ER -
Xiaojun Qiu, Eva Cheng, Ian Burnett. (2016). GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES . IEEE SigPort. http://sigport.org/702
Xiaojun Qiu, Eva Cheng, Ian Burnett, 2016. GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES . Available at: http://sigport.org/702.
Xiaojun Qiu, Eva Cheng, Ian Burnett. (2016). "GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES ." Web.
1. Xiaojun Qiu, Eva Cheng, Ian Burnett. GEOMETRICAL ROOM GEOMETRY ESTIMATION FROM ROOM IMPULSE RESPONSES [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/702

Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification


This paper presents a feature learning approach for speaker identification that is based on nonnegative matrix factorisation. Recent studies have shown that with such models, the dictionary atoms can represent well the speaker identity. The approaches proposed so far focused only on speaker variability and not on session variability. However, this later point is a crucial aspect in the success of the I-vector approach that is now the state-of-the-art in speaker identification.

Paper Details

Authors:
Romain Serizel, Slim Essid, Gaël Richard
Submitted On:
14 March 2016 - 6:42am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

poster_rserizel_ICASSP2016_A4.pdf

(142 downloads)

Keywords

Subscribe

[1] Romain Serizel, Slim Essid, Gaël Richard, "Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/669. Accessed: Jun. 29, 2017.
@article{669-16,
url = {http://sigport.org/669},
author = {Romain Serizel; Slim Essid; Gaël Richard },
publisher = {IEEE SigPort},
title = {Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification},
year = {2016} }
TY - EJOUR
T1 - Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification
AU - Romain Serizel; Slim Essid; Gaël Richard
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/669
ER -
Romain Serizel, Slim Essid, Gaël Richard. (2016). Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification. IEEE SigPort. http://sigport.org/669
Romain Serizel, Slim Essid, Gaël Richard, 2016. Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification. Available at: http://sigport.org/669.
Romain Serizel, Slim Essid, Gaël Richard. (2016). "Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification." Web.
1. Romain Serizel, Slim Essid, Gaël Richard. Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/669

Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides)


Spatial audio reproduction is essential to create a natural listening experience for digital media. Majority of the legacy audio contents are in channel-based format, which is very particular on the desired playback system. Considering the diversity of today’s playback systems, the quality of reproduced sound scenes degrades significantly when mismatches between the audio content and the playback system occur.

Paper Details

Authors:
Submitted On:
2 March 2016 - 4:28am
Short Link:
Type:
Document Year:
Cite

Document Files

ThesisPPT_JianjunHE_2016_SpatialAudioReproductionUsingPrimaryAmbientExtraction.pdf

(173 downloads)

Keywords

Subscribe

[1] , "Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides)", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/608. Accessed: Jun. 29, 2017.
@article{608-16,
url = {http://sigport.org/608},
author = { },
publisher = {IEEE SigPort},
title = {Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides)},
year = {2016} }
TY - EJOUR
T1 - Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides)
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/608
ER -
. (2016). Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides). IEEE SigPort. http://sigport.org/608
, 2016. Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides). Available at: http://sigport.org/608.
. (2016). "Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides)." Web.
1. . Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis slides) [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/608

Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis)


Spatial audio reproduction is essential to create a natural listening experience for digital media. Majority of the legacy audio contents are in channel-based format, which is very particular on the desired playback system. Considering the diversity of today’s playback systems, the quality of reproduced sound scenes degrades significantly when mismatches between the audio content and the playback system occur.

Paper Details

Authors:
Submitted On:
2 March 2016 - 3:54am
Short Link:
Type:
Document Year:
Cite

Document Files

Thesis_JianjunHE_2016_SpatialAudioReproductionUsingPrimaryAmbientExtraction.pdf

(176 downloads)

Keywords

Subscribe

[1] , "Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis)", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/607. Accessed: Jun. 29, 2017.
@article{607-16,
url = {http://sigport.org/607},
author = { },
publisher = {IEEE SigPort},
title = {Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis)},
year = {2016} }
TY - EJOUR
T1 - Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis)
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/607
ER -
. (2016). Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis). IEEE SigPort. http://sigport.org/607
, 2016. Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis). Available at: http://sigport.org/607.
. (2016). "Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis)." Web.
1. . Spatial Audio Reproduction using Primary Ambient Extraction (PhD thesis) [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/607

Fast continuous HRTF acquisition with unconstrained movements of human subjects


Head related transfer function (HRTF) is widely used in 3D audio reproduction, especially over headphones. Conventionally, HRTF database is acquired at discrete directions and the acquisition process is time-consuming. Recent works have been proposed to improve HRTF acquisition efficiency via continuous acquisition. However, these HRTF acquisition techniques still require subject to sit still (with limited head movement) in a rotating chair. In this paper, we further relax the head movement constraint during acquisition by using a head tracker.

Paper Details

Authors:
Rishabh Ranjan
Submitted On:
15 March 2016 - 2:56am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

ICASSP16_JJ_Rish_rev_final - RG version.pdf

(223 downloads)

Keywords

Subscribe

[1] Rishabh Ranjan, "Fast continuous HRTF acquisition with unconstrained movements of human subjects", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/575. Accessed: Jun. 29, 2017.
@article{575-16,
url = {http://sigport.org/575},
author = {Rishabh Ranjan },
publisher = {IEEE SigPort},
title = {Fast continuous HRTF acquisition with unconstrained movements of human subjects},
year = {2016} }
TY - EJOUR
T1 - Fast continuous HRTF acquisition with unconstrained movements of human subjects
AU - Rishabh Ranjan
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/575
ER -
Rishabh Ranjan. (2016). Fast continuous HRTF acquisition with unconstrained movements of human subjects. IEEE SigPort. http://sigport.org/575
Rishabh Ranjan, 2016. Fast continuous HRTF acquisition with unconstrained movements of human subjects. Available at: http://sigport.org/575.
Rishabh Ranjan. (2016). "Fast continuous HRTF acquisition with unconstrained movements of human subjects." Web.
1. Rishabh Ranjan. Fast continuous HRTF acquisition with unconstrained movements of human subjects [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/575

Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques


With the strong growth of the mobile devices and emerging virtual reality (VR) and augmented reality (AR) applications, headsets are becoming more and more preferable in personal listening due to its convenience and portability. Assistive listening (AL) devices like hearing aids have seen much advancement. Creating a natural and authentic listening experience is the common objective of these VR, AR, and AL applications. In this tutorial, we will present state-of-the-art audio and acoustic signal processing techniques to enhance the sound reproduction in headsets and hearing aids.

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Document Year:
Cite

Document Files

APSIPA 2015 Tutorial_GanHe_Assisted listening for headphones and hearing aids.pdf

(251 downloads)

Keywords

Subscribe

[1] , "Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/574. Accessed: Jun. 29, 2017.
@article{574-16,
url = {http://sigport.org/574},
author = { },
publisher = {IEEE SigPort},
title = {Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques},
year = {2016} }
TY - EJOUR
T1 - Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/574
ER -
. (2016). Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques. IEEE SigPort. http://sigport.org/574
, 2016. Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques. Available at: http://sigport.org/574.
. (2016). "Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques." Web.
1. . Tutorial: Assisted Listening for headphones and hearing aids: Signal Processing Techniques [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/574

Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]


Spatial audio reproduction is essential to create a natural listening experience for digital media. Majority of the legacy audio contents are in channel-based format, which is very particular on the desired playback system. Considering the diversity of today's playback systems, the quality of reproduced sound scenes degrades significantly when mismatches between the audio content and the playback system occur. An active sound control approach is required to take the playback system into consideration.

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Document Year:
Cite

Document Files

APSIPA 2015_Apply PAE in spatial audio reproduction.pdf

(194 downloads)

Keywords

Subscribe

[1] , "Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/573. Accessed: Jun. 29, 2017.
@article{573-16,
url = {http://sigport.org/573},
author = { },
publisher = {IEEE SigPort},
title = {Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]},
year = {2016} }
TY - EJOUR
T1 - Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/573
ER -
. (2016). Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]. IEEE SigPort. http://sigport.org/573
, 2016. Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]. Available at: http://sigport.org/573.
. (2016). "Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides]." Web.
1. . Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [slides] [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/573

Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction


Spatial audio reproduction is essential to create a natural listening experience for digital media. Majority of the legacy audio contents are in channel-based format, which is very particular on the desired playback system. Considering the diversity of today's playback systems, the quality of reproduced sound scenes degrades significantly when mismatches between the audio content and the playback system occur. An active sound control approach is required to take the playback system into consideration.

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Document Year:
Cite

Document Files

HeG15_Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction-IEEE approved.pdf

(189 downloads)

Keywords

Subscribe

[1] , "Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/572. Accessed: Jun. 29, 2017.
@article{572-16,
url = {http://sigport.org/572},
author = { },
publisher = {IEEE SigPort},
title = {Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction},
year = {2016} }
TY - EJOUR
T1 - Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/572
ER -
. (2016). Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction. IEEE SigPort. http://sigport.org/572
, 2016. Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction. Available at: http://sigport.org/572.
. (2016). "Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction." Web.
1. . Applying Primary Ambient Extraction for Immersive Spatial Audio Reproduction [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/572

Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation

Paper Details

Authors:
Hatem Deif
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Deif.pdf

(264 downloads)

Keywords

Subscribe

[1] Hatem Deif, "Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/544. Accessed: Jun. 29, 2017.
@article{544-15,
url = {http://sigport.org/544},
author = {Hatem Deif },
publisher = {IEEE SigPort},
title = {Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation},
year = {2015} }
TY - EJOUR
T1 - Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation
AU - Hatem Deif
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/544
ER -
Hatem Deif. (2015). Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation. IEEE SigPort. http://sigport.org/544
Hatem Deif, 2015. Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation. Available at: http://sigport.org/544.
Hatem Deif. (2015). "Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation." Web.
1. Hatem Deif. Non-negative Matrix Factorization and Local Discontinuity Measures for Singing Voice Separation [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/544

Pages