| Presentation | 2020-01-27 Suppression of Dialog System Speech by Embedding Marker Signal into High Frequency Band Shunsuke Saga, Akinori Ito, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Spoken dialog systems have become popular and are used in a home environment, such as smart speakers. A problem will occur when two or more smart speakers are in the same environment, in which a dialog system misdetects the other dialog system’s voice as a user’s voice. In this paper, a method to mute synthesized speech is proposed to prevent a speech recognizer from recognizing speech uttered by a machine. The audio watermark technique is used to indicate that a machine utters the speech, and the speech recognizer attenuates the observed speech if it contains the watermark. The watermark is embedded in high frequency so that the watermark is not perceived by humans and is robustly extracted. From the experimental result, it was found that the proposed method robustly determine the existence of the watermark. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / spoken dialog system / audio watarmarking |
| Paper # | EMM2019-94 |
| Date of Issue | 2020-01-20 (EMM) |
| Conference Information | |
| Committee | EMM |
|---|---|
| Conference Date | 2020/1/27(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tohoku Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Sense of Presence, Universal Media, Digital Entertainment, etc. |
| Chair | Masaki Kawamura(Yamaguchi Univ.) |
| Vice Chair | Motoi Iwata(Osaka Prefecture Univ.) / Tetsuya Kojima(NIT,Tokyo College) |
| Secretary | Motoi Iwata(NIT, Nagano College) / Tetsuya Kojima(Nagase) |
| Assistant | Masaki Inamura(Tokyo Denki Univ.) / Kazuhiro Kono(Kansai Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Enriched MultiMedia |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Suppression of Dialog System Speech by Embedding Marker Signal into High Frequency Band |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | spoken dialog system |
| Keyword(3) | audio watarmarking |
| 1st Author's Name | Shunsuke Saga |
| 1st Author's Affiliation | Tohoku University(Tohoku Univ.) |
| 2nd Author's Name | Akinori Ito |
| 2nd Author's Affiliation | Tohoku University(Tohoku Univ.) |
| Date | 2020-01-27 |
| Paper # | EMM2019-94 |
| Volume (vol) | vol.119 |
| Number (no) | EMM-396 |
| Page | pp.pp.1-6(EMM), |
| #Pages | 6 |
| Date of Issue | 2020-01-20 (EMM) |