EmoBGM: Estimating sound's emotion for creating slideshows with suitable BGM

Cedric Konan, Hirohiko Suwa, Yutaka Arakawa, Keiichi Yasumoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a study about estimating the emotions conveyed in clips of background music (BGM) to be used in an automatic slideshow creation system. The system we aimed to develop, automatically tags each given pieces of background music with the main emotion it conveys, in order to recommend the most suitable music clip to the slideshow creators, based on the main emotions of embedded photos. As a first step of our research, we developed a machine learning model to estimate the emotions conveyed in a music clip and achieved 88% classification accuracy with cross-validation technique. The second part of our work involved developing a web application using Microsoft Emotion API to determine the emotions in photos, so the system can find the best candidate music for each photo in the slideshow. 16 users rated the recommended background music for a set of photos using a 5-point likert scale and we achieved an average rate of 4.1, 3.6 and 3.0 for the photo sets 1, 2, and 3 respectively of our evaluation task.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages351-356
Number of pages6
ISBN (Electronic)9781509043385
DOIs
Publication statusPublished - May 2 2017
Externally publishedYes
Event2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017 - Kona, Big Island, United States
Duration: Mar 13 2017Mar 17 2017

Publication series

Name2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017

Conference

Conference2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017
CountryUnited States
CityKona, Big Island
Period3/13/173/17/17

Fingerprint

Application programming interfaces (API)
Learning systems
Acoustic waves

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Konan, C., Suwa, H., Arakawa, Y., & Yasumoto, K. (2017). EmoBGM: Estimating sound's emotion for creating slideshows with suitable BGM. In 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017 (pp. 351-356). [7917587] (2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PERCOMW.2017.7917587

EmoBGM : Estimating sound's emotion for creating slideshows with suitable BGM. / Konan, Cedric; Suwa, Hirohiko; Arakawa, Yutaka; Yasumoto, Keiichi.

2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 351-356 7917587 (2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Konan, C, Suwa, H, Arakawa, Y & Yasumoto, K 2017, EmoBGM: Estimating sound's emotion for creating slideshows with suitable BGM. in 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017., 7917587, 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017, Institute of Electrical and Electronics Engineers Inc., pp. 351-356, 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017, Kona, Big Island, United States, 3/13/17. https://doi.org/10.1109/PERCOMW.2017.7917587
Konan C, Suwa H, Arakawa Y, Yasumoto K. EmoBGM: Estimating sound's emotion for creating slideshows with suitable BGM. In 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 351-356. 7917587. (2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017). https://doi.org/10.1109/PERCOMW.2017.7917587
Konan, Cedric ; Suwa, Hirohiko ; Arakawa, Yutaka ; Yasumoto, Keiichi. / EmoBGM : Estimating sound's emotion for creating slideshows with suitable BGM. 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 351-356 (2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017).
@inproceedings{1b43998131614771a59c4e1fc70dbd18,
title = "EmoBGM: Estimating sound's emotion for creating slideshows with suitable BGM",
abstract = "This paper presents a study about estimating the emotions conveyed in clips of background music (BGM) to be used in an automatic slideshow creation system. The system we aimed to develop, automatically tags each given pieces of background music with the main emotion it conveys, in order to recommend the most suitable music clip to the slideshow creators, based on the main emotions of embedded photos. As a first step of our research, we developed a machine learning model to estimate the emotions conveyed in a music clip and achieved 88{\%} classification accuracy with cross-validation technique. The second part of our work involved developing a web application using Microsoft Emotion API to determine the emotions in photos, so the system can find the best candidate music for each photo in the slideshow. 16 users rated the recommended background music for a set of photos using a 5-point likert scale and we achieved an average rate of 4.1, 3.6 and 3.0 for the photo sets 1, 2, and 3 respectively of our evaluation task.",
author = "Cedric Konan and Hirohiko Suwa and Yutaka Arakawa and Keiichi Yasumoto",
year = "2017",
month = "5",
day = "2",
doi = "10.1109/PERCOMW.2017.7917587",
language = "English",
series = "2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "351--356",
booktitle = "2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017",
address = "United States",

}

TY - GEN

T1 - EmoBGM

T2 - Estimating sound's emotion for creating slideshows with suitable BGM

AU - Konan, Cedric

AU - Suwa, Hirohiko

AU - Arakawa, Yutaka

AU - Yasumoto, Keiichi

PY - 2017/5/2

Y1 - 2017/5/2

N2 - This paper presents a study about estimating the emotions conveyed in clips of background music (BGM) to be used in an automatic slideshow creation system. The system we aimed to develop, automatically tags each given pieces of background music with the main emotion it conveys, in order to recommend the most suitable music clip to the slideshow creators, based on the main emotions of embedded photos. As a first step of our research, we developed a machine learning model to estimate the emotions conveyed in a music clip and achieved 88% classification accuracy with cross-validation technique. The second part of our work involved developing a web application using Microsoft Emotion API to determine the emotions in photos, so the system can find the best candidate music for each photo in the slideshow. 16 users rated the recommended background music for a set of photos using a 5-point likert scale and we achieved an average rate of 4.1, 3.6 and 3.0 for the photo sets 1, 2, and 3 respectively of our evaluation task.

AB - This paper presents a study about estimating the emotions conveyed in clips of background music (BGM) to be used in an automatic slideshow creation system. The system we aimed to develop, automatically tags each given pieces of background music with the main emotion it conveys, in order to recommend the most suitable music clip to the slideshow creators, based on the main emotions of embedded photos. As a first step of our research, we developed a machine learning model to estimate the emotions conveyed in a music clip and achieved 88% classification accuracy with cross-validation technique. The second part of our work involved developing a web application using Microsoft Emotion API to determine the emotions in photos, so the system can find the best candidate music for each photo in the slideshow. 16 users rated the recommended background music for a set of photos using a 5-point likert scale and we achieved an average rate of 4.1, 3.6 and 3.0 for the photo sets 1, 2, and 3 respectively of our evaluation task.

UR - http://www.scopus.com/inward/record.url?scp=85020117540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020117540&partnerID=8YFLogxK

U2 - 10.1109/PERCOMW.2017.7917587

DO - 10.1109/PERCOMW.2017.7917587

M3 - Conference contribution

AN - SCOPUS:85020117540

T3 - 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017

SP - 351

EP - 356

BT - 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -