AI-Driven Smart Production

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE Mot. Imag. J
Volume: 129, No. 2, pp. 27–35
Abstract: Nippon Hoso Kyokai (NHK, Japan Broadcasting Corporation), has developed a new artificial intelligence (AI)-driven broadcasting technology called “Smart Production” designed to quickly and accurately gather and analyze diverse types of social information and deliver information to a wide range of viewers. Smart Production uses AI to analyze information obtained from social media and open data as well as the know-how related to program production possessed by broadcast stations. This approach makes it possible to extract events and incidents in society and present the results of the analysis to producers. In particular, image analysis technology for recognizing objects in video and speech recognition technology for generating transcripts of interviews enable metadata to be automatically generated for video footage. Additionally, research and development are progressing on technology for automatically converting broadcast data into content that can be easily understood by viewers with special needs.
Publication Date: 2020-03-01
DOI: 10.5594/JMI.2019.2959173
ISSN: Print: 1545-0279 | Electronic: 2160-2492
Link: https://doi.org/10.5594/JMI.2019.2959173
Author(s): Hiroyuki Kaneko
bio
Hiroyuki Kaneko received BE and ME degrees in electric and electronics engineering from Sophia University, Tokyo, Japan, in 2000 and 2002, respectively. He joined NHK (Japan Broadcasting Corp.) in 2002. He has been engaged in research of computer graphics-based content production technology, especially on sign language animation in NHK Science and Technology Research Laboratories (STRL), Tokyo, since 2006.
Jun Goto
bio
Jun Goto received BE and ME degrees in electrical engineering from Tokushima University, Tokushima, Japan, in 1991 and 1993, respectively. He joined NHK in 1993 and has been with NHK Science and Technology Research Laboratories, Tokyo, Japan since 1998. He received a PhD in informatics from the Graduate University for Advanced Study, Hayama, Japan, in 2014. He is currently a senior research engineer at NHK-STRL. His research interests include big data analysis and information extraction based on natural language processing.
Yoshihiko Kawai
bio
Yoshihiko Kawai is a senior manager with NHK Science and Technology Research Laboratories, Tokyo, Japan. He received a PhD degree in engineering from Osaka University, Suita, Japan. His research interests include multimedia processing and video indexing. He is a member of the Institute of Electronics, Information and Communication Engineers (IEICE) and the Institute of Image Information and Television Engineers (ITE), Japan.
Takahiro Mochizuki
bio
Takahiro Mochizuki received BE and ME degrees from the Tokyo Institute of Technology, Tokyo, Japan, in 1994 and 1996, and the PhD degree in engineering from the Tokyo Institute of Technology in 2010. He was with the Outside Broadcasting Technical Division of NHK from 1996 to 1998. Since 1998, he has been working on image processing and recognition with NHK Science and Technology Research Laboratories, Tokyo. His current research focuses on development of video summarization technologies.
Shoei Sato
bio
Shoei Sato received BE and ME degrees from Tohoku University, Sendai, Japan, in 1993. He also received a DrEng degree from Waseda University, Tokyo, Japan, in 2008. From 1995, he was with NHK Science and Technology Research Laboratories, Tokyo. He is currently a senior research engineer with NHK Engineering Systems Inc., Tokyo, and is engaged in speech recognition research for broadcasting. He contributed to the development of live closed-captioning system using speech recognition.
Atsushi Imai
bio
Atsushi Imai received BE degree in electrical engineering from Saitama University, Saitama, Japan, in 1989, and the PhD degree from the University of Tokyo, Tokyo, Japan, in 2014. He joined NHK in 1989. Since 1992, he has been with the Science and Technology Research Laboratories. He is currently a senior research engineer with NHK Engineering Systems Inc., Tokyo. His research interests include the analysis of the hearing and speaking, and the design of aid devices for the disabled
Yuko Yamanouchi
bio
Yuko Yamanouchi received a BE degree in electronic engineering from Sophia University, Tokyo, Japan, in 1986, and ME and PhD degrees in electronic engineering from the Tokyo Institute of Technology, Tokyo, in 1988 and 2005, respectively. She joined NHK in 1988. Since 1990, she has been with NHK Science and Technology Research Laboratories, Tokyo, and she is currently the head of the Smart Production Research Division. She has been engaged in research on image processing and computer graphics technique for TV program production.
Keyword(s): Artificial Intelligence, Audio Description, Big Data, Deep Neural Networks, Image Analysis, Production, Sign Language Animation, Automatic Speech Recognition, Universal Service
Copyright: © 2019 SMPTE

Bibliographic Reference(s)

A. Matsui, T. Mochizuki, Y. Kawai, and R. Endo, “Broadcast Video Summarization using Multimodal Contents Analysis,” IEICE Tech. Rep., PRMU, 2017 (in Japanese). EXTERNAL
R. Endo, Y. Kawai, and T. Mochizuki, “Study of Multi-Scale Residual Network for Image-to-Image Translation,” ITE Tech. Rep., ME, 2017 (in Japanese). EXTERNAL
K. Kurihara, A. Imai, H. Sumiyoshi, Y. Yamanouchi, N. Seiyama, T. Shimizu, S. Sato, I. Yamada, T. Kumano, R. Tako, T. Miyazaki, M. Ichiki, T. Takagi, S. Oshima, and K. Nishida, “Automatic Generation of Audio Descriptions for Sports Program,” presented at IBC2017, Amsterdam, The Netherlands, Sept. 2017. EXTERNAL
T. Uchida, T. Miyazaki, M. Azuma, S. Umeda, N. Kato, H. Sumiyoshi, Y. Yamanouchi, and N. Hiruma, “Sign Language Support System for Viewing Sports Programs,” Proc. ACM ASSETS 2017, pp. 339–340, 2017. EXTERNAL
H. Ito, A. Hagiwara, M. Ichiki, T. Mishima, S. Sato, and A. Kobayashi, “End-to-End Speech Recognition for Languages with Ideographic Characters,” APSIPA ASC, Paper ID 118, 2017. EXTERNAL
J. Goto, T. Miyazaki, Y. Takei, and K. Makino, “Automatic Tweet Detection based on Data Specified through News Production,” Proc. of IUI 2018, no. 1, 2018. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2019.2959173.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Hiroyuki Kaneko, Jun Goto, Yoshihiko Kawai, Takahiro Mochizuki, Shoei Sato, Atsushi Imai, and Yuko Yamanouchi; AI-Driven Smart Production, SMPTE Motion Imaging Journal ( Volume: 129, Issue: 2, March 2020); SMPTE, 2020. Available at https://doi.org/10.5594/JMI.2019.2959173

Snippet:

Hiroyuki Kaneko, Jun Goto, Yoshihiko Kawai, Takahiro Mochizuki, Shoei Sato, Atsushi Imai, and Yuko Yamanouchi; AI-Driven Smart Production, SMPTE Motion Imaging Journal ( Volume: 129, Issue: 2, March 2020); SMPTE, 2020. Available at https://doi.org/10.5594/JMI.2019.2959173

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Hiroyuki Kaneko, Jun Goto, Yoshihiko Kawai, Takahiro Mochizuki, Shoei Sato, Atsushi Imai, and Yuko Yamanouchi; <cite>AI-Driven Smart Production</cite>, SMPTE Motion Imaging Journal ( Volume: 129, Issue: 2, March 2020); SMPTE, 2020. Available at <a href="https://doi.org/10.5594/JMI.2019.2959173" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2019.2959173</a></span>

SMPTE's HTML Pub

Preview:

Hiroyuki Kaneko, Jun Goto, Yoshihiko Kawai, Takahiro Mochizuki, Shoei Sato, Atsushi Imai, and Yuko Yamanouchi; AI-Driven Smart Production, SMPTE Motion Imaging Journal ( Volume: 129, Issue: 2, March 2020); SMPTE, 2020
doi: 10.5594/JMI.2019.2959173
url: https://doi.org/10.5594/JMI.2019.2959173

Snippet:

<li>
Hiroyuki Kaneko, Jun Goto, Yoshihiko Kawai, Takahiro Mochizuki, Shoei Sato, Atsushi Imai, and Yuko Yamanouchi; <cite id="bib-10-5594-jmi-2019-2959173">AI-Driven Smart Production</cite>, SMPTE Motion Imaging Journal ( Volume: 129, Issue: 2, March 2020); SMPTE, 2020
<span class="doi">10.5594/JMI.2019.2959173</span>
</li>