Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song

Hosung PARK; Seungsoo NAM; Eun Man CHOI; Daeseon CHOI

doi:10.1587/transinf.2018EDP7140

IEICE TRANSACTIONS on Information

Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song

Hosung PARK, Seungsoo NAM, Eun Man CHOI, Daeseon CHOI

Full Text Views

0

Cite this

Summary :

Hidden Singer is a television program in Korea. In the show, the original singer and four imitating singers sing a song in hiding behind a screen. The audience and TV viewers attempt to guess who the original singer is by listening to the singing voices. Usually, there are few correct answers from the audience, because the imitators are well trained and highly skilled. We propose a computerized system for distinguishing the original singer from the imitating singers. During the training phase, the system learns only the original singer's song because it is the one the audience has heard before. During the testing phase, the songs of five candidates are provided to the system and the system then determines the original singer. The system uses a 1-class authentication method, in which only a subject model is made. The subject model is used for measuring similarities between the candidate songs. In this problem, unlike other existing studies that require artist identification, we cannot utilize multi-class classifiers and supervised learning because songs of the imitators and the labels are not provided during the training phase. Therefore, we evaluate the performances of several 1-class learning algorithms to choose which one is more efficient in distinguishing an original singer from among highly skilled imitators. The experiment results show that the proposed system using the autoencoder performs better (63.33%) than other 1-class learning algorithms: Gaussian mixture model (GMM) (50%) and one class support vector machines (OCSVM) (26.67%). We also conduct a human contest to compare the performance of the proposed system with human perception. The accuracy of the proposed system is found to be better (63.33%) than the average accuracy of human perception (33.48%).

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.12 pp.3092-3101

Publication Date: 2018/12/01

Publicized: 2018/08/24

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2018EDP7140

Type of Manuscript: PAPER

Category: Artificial Intelligence, Data Mining

Authors

Hosung PARK
  Kongju National University
Seungsoo NAM
  Kongju National University
Eun Man CHOI
  Dongguk University
Daeseon CHOI
  Kongju National University

Keyword

singer authentication, autoencoder, neural network, artificial intelligence

Cite this

Copy

Hosung PARK, Seungsoo NAM, Eun Man CHOI, Daeseon CHOI, "Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 12, pp. 3092-3101, December 2018, doi: 10.1587/transinf.2018EDP7140.
Abstract: Hidden Singer is a television program in Korea. In the show, the original singer and four imitating singers sing a song in hiding behind a screen. The audience and TV viewers attempt to guess who the original singer is by listening to the singing voices. Usually, there are few correct answers from the audience, because the imitators are well trained and highly skilled. We propose a computerized system for distinguishing the original singer from the imitating singers. During the training phase, the system learns only the original singer's song because it is the one the audience has heard before. During the testing phase, the songs of five candidates are provided to the system and the system then determines the original singer. The system uses a 1-class authentication method, in which only a subject model is made. The subject model is used for measuring similarities between the candidate songs. In this problem, unlike other existing studies that require artist identification, we cannot utilize multi-class classifiers and supervised learning because songs of the imitators and the labels are not provided during the training phase. Therefore, we evaluate the performances of several 1-class learning algorithms to choose which one is more efficient in distinguishing an original singer from among highly skilled imitators. The experiment results show that the proposed system using the autoencoder performs better (63.33%) than other 1-class learning algorithms: Gaussian mixture model (GMM) (50%) and one class support vector machines (OCSVM) (26.67%). We also conduct a human contest to compare the performance of the proposed system with human perception. The accuracy of the proposed system is found to be better (63.33%) than the average accuracy of human perception (33.48%).
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7140/_p

Copy

@ARTICLE{e101-d_12_3092,
author={Hosung PARK, Seungsoo NAM, Eun Man CHOI, Daeseon CHOI, },
journal={IEICE TRANSACTIONS on Information},
title={Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song},
year={2018},
volume={E101-D},
number={12},
pages={3092-3101},
abstract={Hidden Singer is a television program in Korea. In the show, the original singer and four imitating singers sing a song in hiding behind a screen. The audience and TV viewers attempt to guess who the original singer is by listening to the singing voices. Usually, there are few correct answers from the audience, because the imitators are well trained and highly skilled. We propose a computerized system for distinguishing the original singer from the imitating singers. During the training phase, the system learns only the original singer's song because it is the one the audience has heard before. During the testing phase, the songs of five candidates are provided to the system and the system then determines the original singer. The system uses a 1-class authentication method, in which only a subject model is made. The subject model is used for measuring similarities between the candidate songs. In this problem, unlike other existing studies that require artist identification, we cannot utilize multi-class classifiers and supervised learning because songs of the imitators and the labels are not provided during the training phase. Therefore, we evaluate the performances of several 1-class learning algorithms to choose which one is more efficient in distinguishing an original singer from among highly skilled imitators. The experiment results show that the proposed system using the autoencoder performs better (63.33%) than other 1-class learning algorithms: Gaussian mixture model (GMM) (50%) and one class support vector machines (OCSVM) (26.67%). We also conduct a human contest to compare the performance of the proposed system with human perception. The accuracy of the proposed system is found to be better (63.33%) than the average accuracy of human perception (33.48%).},
keywords={},
doi={10.1587/transinf.2018EDP7140},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Hidden Singer: Distinguishing Imitation Singers Based on Training with Only the Original Song
T2 - IEICE TRANSACTIONS on Information
SP - 3092
EP - 3101
AU - Hosung PARK
AU - Seungsoo NAM
AU - Eun Man CHOI
AU - Daeseon CHOI
PY - 2018
DO - 10.1587/transinf.2018EDP7140
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2018
AB - Hidden Singer is a television program in Korea. In the show, the original singer and four imitating singers sing a song in hiding behind a screen. The audience and TV viewers attempt to guess who the original singer is by listening to the singing voices. Usually, there are few correct answers from the audience, because the imitators are well trained and highly skilled. We propose a computerized system for distinguishing the original singer from the imitating singers. During the training phase, the system learns only the original singer's song because it is the one the audience has heard before. During the testing phase, the songs of five candidates are provided to the system and the system then determines the original singer. The system uses a 1-class authentication method, in which only a subject model is made. The subject model is used for measuring similarities between the candidate songs. In this problem, unlike other existing studies that require artist identification, we cannot utilize multi-class classifiers and supervised learning because songs of the imitators and the labels are not provided during the training phase. Therefore, we evaluate the performances of several 1-class learning algorithms to choose which one is more efficient in distinguishing an original singer from among highly skilled imitators. The experiment results show that the proposed system using the autoencoder performs better (63.33%) than other 1-class learning algorithms: Gaussian mixture model (GMM) (50%) and one class support vector machines (OCSVM) (26.67%). We also conduct a human contest to compare the performance of the proposed system with human perception. The accuracy of the proposed system is found to be better (63.33%) than the average accuracy of human perception (33.48%).
ER -

IEICE TRANSACTIONS on Information