SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019)
[ACTIVE]
Automatic Generation of Audio Descriptions for Sports Programs
Metadata
- Publisher
- SMPTE — White Plains, NY, USA
- Doc Type
- Journal Article
- Content Type
- Original Research
- Abbreviated Title
- SMPTE Mot. Imag. J
- Volume
- 128, No. 1, pp. 41–47
- Abstract
- The Japan Broadcasting Corporation (NHK) has developed a means of automatically generating auxiliary audio descriptions from metadata for use in live TV sports programs. Audio description services are important for helping visually impaired persons enjoy TV programs, but such services are currently available for only a handful of programs because many studio resources and personnel are required to create audio descriptions, and it is especially difficult to produce such descriptions during live broadcasts. The method described in this paper has the potential to overcome these obstacles. The system that we constructed for the Rio Olympic and Paralympic Games consists of commentary text generation and text-to-speech (TTS) processes. The commentary text generation process generates commentary appropriate to the situation for each piece of event data accepted by the system, and the TTS part converts it into natural speech. We ran the system during the Rio Olympic and Paralympic Games, and it provided both caption and audio descriptions for more than 2,000 sporting contests.
- Publication Date
- 2019-01-01
- DOI
10.5594/JMI.2018.2879261- ISSN
- Print:
1545-0279| Electronic:2160-2492 - Link
- https://doi.org/10.5594/JMI.2018.2879261
- Author(s)
- Kiyoshi KuriharaAtsushi ImaiNobumasa SeiyamaToshihiro ShimizuShoei SatoIchiro YamadaTadashi KumanoReiko TakoTaro MiyazakiManon IchikiTohru TakagiHideki Sumiyoshi
- Keyword(s)
- Audio Description, Sports Metadata, Sports Commentary, Text-to-Speech
- Copyright
- © 2018 SMPTE
Bibliographic Reference(s)
- Ministry of Internal Affairs and Communications, “Actual Results of Attachment of Closed Caption and Others in 2015,” 2014. [Online]. Available: http://www.soumu.go.jp/menu_news/s-news/ 01ryutsu09_02000126.html (in Japanese). EXTERNAL
- K. Kurihara et al., “The DNN-Based Speech Synthesis Using Speaker Codes and Emotional Codes,” Proc. IEICE General Conf. 2017, vol. 2017, D-14-10, 2017 (in Japanese). EXTERNAL
- S. Jose et al., “char2wav: End-to-End Speech Synthesis,” presented at ICLR 2017, Toulon, France, April 2017. EXTERNAL
- T. Miyazaki et al., “Automatic Generation of Audio Description for Olympics/Paralympics Programs,” presented at NAB Show 2017, Las Vegas, NV, April 2017. EXTERNAL
- Japan Broadcasting Corporation, “On the Overview of the PyeongChang 2018 Winter Olympic and Paralympic Games,” 2017. [Online]. Available: https://www.nhk.or.jp/corporateinfo/english/comment_top/president/2017/1712.html EXTERNAL
- A. Van den Oord et al., “A Generative Model for Raw Audio,” CoRR abs, 1609.03499. EXTERNAL
- Olympic Broadcasting Services, “The International Signal, About OBS,” 2017. [Online]. Available: https://www.obs.tv EXTERNAL
- AI Inc., “What is AITalk,” 2017. [Online]. Available: http://www.ai-j.jp/english EXTERNAL
- Y. Wang et al., “Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model,” arXiv preprint arXiv, 1703.10135, 2017. EXTERNAL
- Olympic Broadcasting Services, “On-Venue Results and Timing,” Broadcaster Manual Rio 2016 Olympic Games, pp. 84–85, 2015. EXTERNAL
- International Olympic Committee, “Olympic Data Feed,” 2017. [Online]. Available: http://odf.olympictech.org EXTERNAL
- H. Zen, A. Senior, and M. Schuster, “Statistical Parametric Speech Synthesis Using Deep Neural Networks,” Proc. ICASSP, pp. 8012–8016, 2013. EXTERNAL
Source Data (JSON)
Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2018.2879261.json
Reference Tree
Explore all references and references to this document, as a navigable tree.
Open Reference TreeReference this Doc
Plain text (ISO 690 compliant)
Preview:
Kiyoshi Kurihara, Atsushi Imai, Nobumasa Seiyama, Toshihiro Shimizu, Shoei Sato, Ichiro Yamada, Tadashi Kumano, Reiko Tako, Taro Miyazaki, Manon Ichiki, Tohru Takagi, and Hideki Sumiyoshi; Automatic Generation of Audio Descriptions for Sports Programs, SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019); SMPTE, 2019. Available at https://doi.org/10.5594/JMI.2018.2879261
Snippet:
Kiyoshi Kurihara, Atsushi Imai, Nobumasa Seiyama, Toshihiro Shimizu, Shoei Sato, Ichiro Yamada, Tadashi Kumano, Reiko Tako, Taro Miyazaki, Manon Ichiki, Tohru Takagi, and Hideki Sumiyoshi; Automatic Generation of Audio Descriptions for Sports Programs, SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019); SMPTE, 2019. Available at https://doi.org/10.5594/JMI.2018.2879261
HTML (ISO 690 compliant)
Preview:
Kiyoshi Kurihara, Atsushi Imai, Nobumasa Seiyama, Toshihiro Shimizu, Shoei Sato, Ichiro Yamada, Tadashi Kumano, Reiko Tako, Taro Miyazaki, Manon Ichiki, Tohru Takagi, and Hideki Sumiyoshi; Automatic Generation of Audio Descriptions for Sports Programs, SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019); SMPTE, 2019. Available at https://doi.org/10.5594/JMI.2018.2879261
Snippet:
<span class="citation">Kiyoshi Kurihara, Atsushi Imai, Nobumasa Seiyama, Toshihiro Shimizu, Shoei Sato, Ichiro Yamada, Tadashi Kumano, Reiko Tako, Taro Miyazaki, Manon Ichiki, Tohru Takagi, and Hideki Sumiyoshi; <cite>Automatic Generation of Audio Descriptions for Sports Programs</cite>, SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019); SMPTE, 2019. Available at <a href="https://doi.org/10.5594/JMI.2018.2879261" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2018.2879261</a></span>
SMPTE's HTML Pub
Preview:
Kiyoshi Kurihara, Atsushi Imai, Nobumasa Seiyama, Toshihiro Shimizu, Shoei Sato, Ichiro Yamada, Tadashi Kumano, Reiko Tako, Taro Miyazaki, Manon Ichiki, Tohru Takagi, and Hideki Sumiyoshi; Automatic Generation of Audio Descriptions for Sports Programs, SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019); SMPTE, 2019
doi: 10.5594/JMI.2018.2879261
url: https://doi.org/10.5594/JMI.2018.2879261
doi: 10.5594/JMI.2018.2879261
url: https://doi.org/10.5594/JMI.2018.2879261
Snippet:
<li> Kiyoshi Kurihara, Atsushi Imai, Nobumasa Seiyama, Toshihiro Shimizu, Shoei Sato, Ichiro Yamada, Tadashi Kumano, Reiko Tako, Taro Miyazaki, Manon Ichiki, Tohru Takagi, and Hideki Sumiyoshi; <cite id="bib-10-5594-jmi-2018-2879261">Automatic Generation of Audio Descriptions for Sports Programs</cite>, SMPTE Motion Imaging Journal ( Volume: 128, Issue: 1, 2019); SMPTE, 2019 <span class="doi">10.5594/JMI.2018.2879261</span> </li>