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

ICASSP 2019

ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The 2019 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world. Visit website

HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?


Video Object Tracking -VOT- in realistic scenarios is a difficult task. Image factors such as occlusion, clutter, confusion, object shape, and zooming, among others, have an impact on video tracker methods performance. While these conditions do affect trackers performance, there is not a clear distinction between the scene content challenges like occlusion and clutter, against challenges due to distortions generated by capture, compression, processing, and transmission of videos. This paper is concerned with the latter interpretation of quality as it affects VOT performance.

Paper Details

Authors:
Hernan Dario Benitez Restrepo, Ivan Cabezas
Submitted On:
7 May 2019 - 8:25pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ObjectTracking_4127

(51)

Keywords

Additional Categories

Subscribe

[1] Hernan Dario Benitez Restrepo, Ivan Cabezas, "HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3973. Accessed: Apr. 04, 2020.
@article{3973-19,
url = {http://sigport.org/3973},
author = {Hernan Dario Benitez Restrepo; Ivan Cabezas },
publisher = {IEEE SigPort},
title = {HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?},
year = {2019} }
TY - EJOUR
T1 - HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?
AU - Hernan Dario Benitez Restrepo; Ivan Cabezas
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3973
ER -
Hernan Dario Benitez Restrepo, Ivan Cabezas. (2019). HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?. IEEE SigPort. http://sigport.org/3973
Hernan Dario Benitez Restrepo, Ivan Cabezas, 2019. HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?. Available at: http://sigport.org/3973.
Hernan Dario Benitez Restrepo, Ivan Cabezas. (2019). "HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS?." Web.
1. Hernan Dario Benitez Restrepo, Ivan Cabezas. HOW VIDEO OBJECT TRACKING IS AFFECTED BY IN-CAPTURE DISTORTIONS? [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3973

SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC


The localization of acoustic sound sources is beneficial to signal processing applications of speech enhancement, dereverberation, separation and tracking. Difficulties in position estimation arise in real world environments due to coherent reflections degrading performance of subspace localization techniques. This paper proposes a method of multiple signal classification (MUSIC) subspace localization, which is suitable for reverberant rooms. The method is based on the modal decomposition of a room's region-to-region transfer function, which is assumed to be known.

Paper Details

Authors:
Lachlan Birnie, Thushara Abhayapala, Hanchi Chen, Prasanga Samarasinghe
Submitted On:
7 May 2019 - 8:15pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

u5351515_lachlan_birnie_ICASSP2019_Poster.pdf

(59)

Subscribe

[1] Lachlan Birnie, Thushara Abhayapala, Hanchi Chen, Prasanga Samarasinghe, "SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3972. Accessed: Apr. 04, 2020.
@article{3972-19,
url = {http://sigport.org/3972},
author = {Lachlan Birnie; Thushara Abhayapala; Hanchi Chen; Prasanga Samarasinghe },
publisher = {IEEE SigPort},
title = {SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC},
year = {2019} }
TY - EJOUR
T1 - SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC
AU - Lachlan Birnie; Thushara Abhayapala; Hanchi Chen; Prasanga Samarasinghe
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3972
ER -
Lachlan Birnie, Thushara Abhayapala, Hanchi Chen, Prasanga Samarasinghe. (2019). SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC. IEEE SigPort. http://sigport.org/3972
Lachlan Birnie, Thushara Abhayapala, Hanchi Chen, Prasanga Samarasinghe, 2019. SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC. Available at: http://sigport.org/3972.
Lachlan Birnie, Thushara Abhayapala, Hanchi Chen, Prasanga Samarasinghe. (2019). "SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC." Web.
1. Lachlan Birnie, Thushara Abhayapala, Hanchi Chen, Prasanga Samarasinghe. SOUND SOURCE LOCALIZATION IN A REVERBERANT ROOM USING HARMONIC BASED MUSIC [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3972

Learning Shared Vector Representations of Lyrics and Chords in Music


Music has a powerful influence on a listener's emotions. In this paper, we represent lyrics and chords in a shared vector space using a phrase-aligned chord-and-lyrics corpus. We show that models that use these shared representations predict a listener's emotion while hearing musical passages better than models that do not use these representations. Additionally, we conduct a visual analysis of these learnt shared vector representations and explain how they support existing theories in music.

Paper Details

Authors:
Timothy Greer, Karan Singla, Benjamin Ma, and Shrikanth Narayanan
Submitted On:
7 May 2019 - 8:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Learning_Shared_Reps_ICASSP_Pres_2(1).pdf

(82)

Subscribe

[1] Timothy Greer, Karan Singla, Benjamin Ma, and Shrikanth Narayanan, "Learning Shared Vector Representations of Lyrics and Chords in Music", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3971. Accessed: Apr. 04, 2020.
@article{3971-19,
url = {http://sigport.org/3971},
author = {Timothy Greer; Karan Singla; Benjamin Ma; and Shrikanth Narayanan },
publisher = {IEEE SigPort},
title = {Learning Shared Vector Representations of Lyrics and Chords in Music},
year = {2019} }
TY - EJOUR
T1 - Learning Shared Vector Representations of Lyrics and Chords in Music
AU - Timothy Greer; Karan Singla; Benjamin Ma; and Shrikanth Narayanan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3971
ER -
Timothy Greer, Karan Singla, Benjamin Ma, and Shrikanth Narayanan. (2019). Learning Shared Vector Representations of Lyrics and Chords in Music. IEEE SigPort. http://sigport.org/3971
Timothy Greer, Karan Singla, Benjamin Ma, and Shrikanth Narayanan, 2019. Learning Shared Vector Representations of Lyrics and Chords in Music. Available at: http://sigport.org/3971.
Timothy Greer, Karan Singla, Benjamin Ma, and Shrikanth Narayanan. (2019). "Learning Shared Vector Representations of Lyrics and Chords in Music." Web.
1. Timothy Greer, Karan Singla, Benjamin Ma, and Shrikanth Narayanan. Learning Shared Vector Representations of Lyrics and Chords in Music [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3971

Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region


Active Noise Cancellation (ANC) is a well researched topic for minimizing unwanted acoustic noise, and spatial ANC is a recently introduced concept that focuses on continuous spatial regions. Adaptive filter designing for spatial ANC is often based on frequency-domain spherical harmonic decomposition method, which has a major limitation due to the increased system latency. In this paper, we develop a time-domain spherical harmonic based signal decomposition method and use it to develop two time-space domain feed-forward adaptive filters for spatial ANC.

Paper Details

Authors:
Huiyuan Sun, Thushara D. Abhayapala, Prasanga N. Samarasinghe
Submitted On:
7 May 2019 - 8:13pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP_POSTER_decided.pdf

(54)

Subscribe

[1] Huiyuan Sun, Thushara D. Abhayapala, Prasanga N. Samarasinghe, "Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3970. Accessed: Apr. 04, 2020.
@article{3970-19,
url = {http://sigport.org/3970},
author = {Huiyuan Sun; Thushara D. Abhayapala; Prasanga N. Samarasinghe },
publisher = {IEEE SigPort},
title = {Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region},
year = {2019} }
TY - EJOUR
T1 - Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region
AU - Huiyuan Sun; Thushara D. Abhayapala; Prasanga N. Samarasinghe
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3970
ER -
Huiyuan Sun, Thushara D. Abhayapala, Prasanga N. Samarasinghe. (2019). Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region. IEEE SigPort. http://sigport.org/3970
Huiyuan Sun, Thushara D. Abhayapala, Prasanga N. Samarasinghe, 2019. Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region. Available at: http://sigport.org/3970.
Huiyuan Sun, Thushara D. Abhayapala, Prasanga N. Samarasinghe. (2019). "Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region." Web.
1. Huiyuan Sun, Thushara D. Abhayapala, Prasanga N. Samarasinghe. Time domain Spherical harmonic analysis for adaptive noise cancellation over a spatial region [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3970

A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED


This work proposes a new neural network framework to simultaneously rank multiple hypotheses generated by one or more automatic speech recognition (ASR) engines for a speech utterance. Features fed in the framework not only include those calculated from the ASR information, but also involve natural language understanding (NLU) related features, such as trigger features capturing long-distance constraints between word/slot pairs and BLSTM features representing intent-sensitive sentence embedding.

Paper Details

Authors:
Zhengyu Zhou, Xuchen Song, Rami Botros, Lin Zhao
Submitted On:
7 May 2019 - 7:57pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_ICASSP2019.pdf

(110)

Subscribe

[1] Zhengyu Zhou, Xuchen Song, Rami Botros, Lin Zhao, "A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3969. Accessed: Apr. 04, 2020.
@article{3969-19,
url = {http://sigport.org/3969},
author = {Zhengyu Zhou; Xuchen Song; Rami Botros; Lin Zhao },
publisher = {IEEE SigPort},
title = {A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED},
year = {2019} }
TY - EJOUR
T1 - A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED
AU - Zhengyu Zhou; Xuchen Song; Rami Botros; Lin Zhao
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3969
ER -
Zhengyu Zhou, Xuchen Song, Rami Botros, Lin Zhao. (2019). A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED. IEEE SigPort. http://sigport.org/3969
Zhengyu Zhou, Xuchen Song, Rami Botros, Lin Zhao, 2019. A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED. Available at: http://sigport.org/3969.
Zhengyu Zhou, Xuchen Song, Rami Botros, Lin Zhao. (2019). "A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED." Web.
1. Zhengyu Zhou, Xuchen Song, Rami Botros, Lin Zhao. A NEURAL NETWORK BASED RANKING FRAMEWORK TO IMPROVE ASR WITH NLU RELATED KNOWLEDGE DEPLOYED [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3969

Variational and Hierarchical Recurrent Autoencoder


Despite a great success in learning representation for image data, it is challenging to learn the stochastic latent features from natural language based on variational inference. The difficulty in stochastic sequential learning is due to the posterior collapse caused by an autoregressive decoder which is prone to be too strong to learn sufficient latent information during optimization. To compensate this weakness in learning procedure, a sophisticated latent structure is required to assure good convergence so that random features are sufficiently captured for sequential decoding.

Paper Details

Authors:
Jen-Tzung Chien and Chun-Wei Wang
Submitted On:
7 May 2019 - 8:19pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

[ICASSP 2019] Variational and hierarchical recurrent autoencoder.pdf

(101)

Icassp19_hier.pdf

(69)

Subscribe

[1] Jen-Tzung Chien and Chun-Wei Wang, "Variational and Hierarchical Recurrent Autoencoder", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3968. Accessed: Apr. 04, 2020.
@article{3968-19,
url = {http://sigport.org/3968},
author = {Jen-Tzung Chien and Chun-Wei Wang },
publisher = {IEEE SigPort},
title = {Variational and Hierarchical Recurrent Autoencoder},
year = {2019} }
TY - EJOUR
T1 - Variational and Hierarchical Recurrent Autoencoder
AU - Jen-Tzung Chien and Chun-Wei Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3968
ER -
Jen-Tzung Chien and Chun-Wei Wang. (2019). Variational and Hierarchical Recurrent Autoencoder. IEEE SigPort. http://sigport.org/3968
Jen-Tzung Chien and Chun-Wei Wang, 2019. Variational and Hierarchical Recurrent Autoencoder. Available at: http://sigport.org/3968.
Jen-Tzung Chien and Chun-Wei Wang. (2019). "Variational and Hierarchical Recurrent Autoencoder." Web.
1. Jen-Tzung Chien and Chun-Wei Wang. Variational and Hierarchical Recurrent Autoencoder [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3968

COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION


Despite the great advances, most of the recently developed automatic speech recognition systems focus on working in a server-client manner, and thus often require a high computational cost, such as the storage size and memory accesses. This, however, does not satisfy the increasing demand for a succinct model that can run smoothly in embedded devices like smartphones.

Paper Details

Authors:
Huan Zhao, Yufeng Xiao, Jing Han, Zixing Zhang
Submitted On:
7 May 2019 - 7:10pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICASSP19005.pdf

(63)

Keywords

Additional Categories

Subscribe

[1] Huan Zhao, Yufeng Xiao, Jing Han, Zixing Zhang, "COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3967. Accessed: Apr. 04, 2020.
@article{3967-19,
url = {http://sigport.org/3967},
author = {Huan Zhao; Yufeng Xiao; Jing Han; Zixing Zhang },
publisher = {IEEE SigPort},
title = {COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION
AU - Huan Zhao; Yufeng Xiao; Jing Han; Zixing Zhang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3967
ER -
Huan Zhao, Yufeng Xiao, Jing Han, Zixing Zhang. (2019). COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION. IEEE SigPort. http://sigport.org/3967
Huan Zhao, Yufeng Xiao, Jing Han, Zixing Zhang, 2019. COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION. Available at: http://sigport.org/3967.
Huan Zhao, Yufeng Xiao, Jing Han, Zixing Zhang. (2019). "COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION." Web.
1. Huan Zhao, Yufeng Xiao, Jing Han, Zixing Zhang. COMPACT CONVOLUTIONAL RECURRENT NEURAL NETWORKS VIA BINARIZATION FOR SPEECH EMOTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3967

ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)

Paper Details

Authors:
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps
Submitted On:
7 May 2019 - 6:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019_Poster_TharshiniGunendradasan.pptx

(73)

Subscribe

[1] Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps, "ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3966. Accessed: Apr. 04, 2020.
@article{3966-19,
url = {http://sigport.org/3966},
author = {Tharshini Gunendradasan; Saad Irtza; Eliathamby Ambikairajah; Julien Epps },
publisher = {IEEE SigPort},
title = {ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)},
year = {2019} }
TY - EJOUR
T1 - ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)
AU - Tharshini Gunendradasan; Saad Irtza; Eliathamby Ambikairajah; Julien Epps
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3966
ER -
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps. (2019). ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION). IEEE SigPort. http://sigport.org/3966
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps, 2019. ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION). Available at: http://sigport.org/3966.
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps. (2019). "ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)." Web.
1. Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps. ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION) [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3966

ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)

Paper Details

Authors:
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps
Submitted On:
7 May 2019 - 6:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019_Poster_TharshiniGunendradasan.pdf

(111)

Subscribe

[1] Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps, "ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3965. Accessed: Apr. 04, 2020.
@article{3965-19,
url = {http://sigport.org/3965},
author = {Tharshini Gunendradasan; Saad Irtza; Eliathamby Ambikairajah; Julien Epps },
publisher = {IEEE SigPort},
title = {ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)},
year = {2019} }
TY - EJOUR
T1 - ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)
AU - Tharshini Gunendradasan; Saad Irtza; Eliathamby Ambikairajah; Julien Epps
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3965
ER -
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps. (2019). ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION). IEEE SigPort. http://sigport.org/3965
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps, 2019. ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION). Available at: http://sigport.org/3965.
Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps. (2019). "ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION)." Web.
1. Tharshini Gunendradasan, Saad Irtza, Eliathamby Ambikairajah, Julien Epps. ICASSP 2019 Poster (TRANSMISSION LINE COCHLEAR MODEL BASED AM-FM FEATURES FOR REPLAY ATTACK DETECTION) [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3965

MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION


For many music analysis problems, we need to know the presence
of instruments for each time frame in a multi-instrument
musical piece. However, such a frame-level instrument recognition
task remains difficult, mainly due to the lack of labeled
datasets. To address this issue, we present in this paper a
large-scale dataset that contains synthetic polyphonic music
with frame-level pitch and instrument labels. Moreover, we
propose a simple yet novel network architecture to jointly predict

Paper Details

Authors:
Yun-Ning Hung, Yi-An Chen, Yi-Hsuan Yang
Submitted On:
7 May 2019 - 6:02pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

multitask learning-icassp2019-poster.pdf

(41)

Subscribe

[1] Yun-Ning Hung, Yi-An Chen, Yi-Hsuan Yang , "MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3964. Accessed: Apr. 04, 2020.
@article{3964-19,
url = {http://sigport.org/3964},
author = {Yun-Ning Hung; Yi-An Chen; Yi-Hsuan Yang },
publisher = {IEEE SigPort},
title = {MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION
AU - Yun-Ning Hung; Yi-An Chen; Yi-Hsuan Yang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3964
ER -
Yun-Ning Hung, Yi-An Chen, Yi-Hsuan Yang . (2019). MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION. IEEE SigPort. http://sigport.org/3964
Yun-Ning Hung, Yi-An Chen, Yi-Hsuan Yang , 2019. MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION. Available at: http://sigport.org/3964.
Yun-Ning Hung, Yi-An Chen, Yi-Hsuan Yang . (2019). "MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION." Web.
1. Yun-Ning Hung, Yi-An Chen, Yi-Hsuan Yang . MULTITASK LEARNING FOR FRAME-LEVEL INSTRUMENT RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3964

Pages