| Presentation | 2016-11-18 Voice Actor Recognition Using Frequency Spectrum in Anime Video Motoki Eida, Shun Hattori, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | When we hear someone's voice from an anime video, we need to carry extra burdens of searching the end roll of the anime video in order to know about whose voice it is. If a system can recognize a voice actor from his/her voice on behalf of us, not only we can know about the voice actor's name without carrying extra burdens, but also we can acquire widely information about him/her such as his/her appearance information, blogs, related videos, related goods, and event information in the future. Our previous research has been tackling a system of voice actor recognition with filtering by cast information extracted from the Web and similarity calculation based on voice amplitude, but the system could not give enough good performance as voice actor recognition accuracy. Therefore, this paper proposes a novel system of voice actor recognition that utilizes not voice amplitude but frequency power spectrum. Our proposed system identifies the "characteristic power spectrum" for each of individual voice actors who are registered in the database of the system by auto-correlation analysis in advance, and recognizes a voice actor from a voice in a playing anime video by comparing the voice's frequency power spectrum with each individual voice actor's characteristic power spectrum registered in the database. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Voice Actor Recognition / Speech Recognition / Characteristic Power Spectrum / Auto-Correlation |
| Paper # | IN2016-64 |
| Date of Issue | 2016-11-10 (IN) |
| Conference Information | |
| Committee | IN / MoNA / CNR |
|---|---|
| Conference Date | 2016/11/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kirishima-kanko Hotel |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | M2M, IoT, Self Organization, Autonomous Distributed Control, Car Area Network, Car-Car network, Car-Road Network, ITS, Big Data Analysis, Cyber Physical System (CPS), Security Privacy Protection, Social Network (SNS), Cyber Attack resolution, Mobile Virtualization, Mobile Application, Cloud Robotics Service, etc. |
| Chair | Katsunori Yamaoka(Tokyo Inst. of Tech.) / Hiroaki Morino(Shibaura Inst. of Tech.) / Michita Imai(Keio Univ.) |
| Vice Chair | Takuji Kishida(NTT) / Ryoichi Shinkuma(Kyoto Univ.) / Tetsuo Ono(Hokkaido Univ.) / Masayuki Kanbara(NAIST) |
| Secretary | Takuji Kishida(KDDI R&D Labs.) / Ryoichi Shinkuma(NTT) / Tetsuo Ono(Univ. of Tokyo) / Masayuki Kanbara(NTT DoCoMo) |
| Assistant | Kunitake Kaneko(Keio Univ.) / Takashi Natsume(NTT) / Shigemi Ishida(Kyushu Univ.) / Hisashi Kurasawa(NTT) / Koichi Nihei(NEC) / Kosuke Yoshioka(Panasonic) / Daisuke Yamamoto(Toshiba) / Takahiro Matsumoto(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Mobile Network and Applications / Technical Committee on Cloud Network Robotics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Voice Actor Recognition Using Frequency Spectrum in Anime Video |
| Sub Title (in English) | |
| Keyword(1) | Voice Actor Recognition |
| Keyword(2) | Speech Recognition |
| Keyword(3) | Characteristic Power Spectrum |
| Keyword(4) | Auto-Correlation |
| 1st Author's Name | Motoki Eida |
| 1st Author's Affiliation | Muroran Institute of Technology(Muroran Inst. of Tech.) |
| 2nd Author's Name | Shun Hattori |
| 2nd Author's Affiliation | Muroran Institute of Technology(Muroran Inst. of Tech.) |
| Date | 2016-11-18 |
| Paper # | IN2016-64 |
| Volume (vol) | vol.116 |
| Number (no) | IN-304 |
| Page | pp.pp.25-30(IN), |
| #Pages | 6 |
| Date of Issue | 2016-11-10 (IN) |