| Presentation | 2024-03-14 Consideration on divisions and combinations of Learning Data for Speaker Diarization in Multiple Speakers Kaito Uemura, Keiichi Horio, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Today, the importance of a speech segment detection technique called speaker diarization is increasing, mainly in the fields of conference, news, and telephone speech. However, conventional neural network-based speaker diarization assumes a large amount of training data. In this study, training data was generated by recording the speech of two speakers of the same gender and creating a synthetic voice by splitting and combining them. The effect of the number of segmentations and combinations on the accuracy of the test data was verified. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Diarization / Bidirectional LSTM / voice recognition |
| Paper # | SIS2023-48 |
| Date of Issue | 2024-03-07 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2024/3/14(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kanagawa Institute of Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Soft computing, etc. |
| Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) |
| Vice Chair | Naoto Sasaoka(Tottori Univ.) / Hakaru Tamukoh(Kyushu Inst. of Tech.) |
| Secretary | Naoto Sasaoka(Kanagawa Inst. of Tech.) / Hakaru Tamukoh(Kansai Univ.) |
| Assistant | Yuichiro Tanaka(kyushu Inst. of Tech.) / Yosuke Sugiura(Saitama Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Consideration on divisions and combinations of Learning Data for Speaker Diarization in Multiple Speakers |
| Sub Title (in English) | |
| Keyword(1) | Diarization |
| Keyword(2) | Bidirectional LSTM |
| Keyword(3) | voice recognition |
| 1st Author's Name | Kaito Uemura |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyushu Institute of Technology) |
| 2nd Author's Name | Keiichi Horio |
| 2nd Author's Affiliation | Kyushu Institute of Technology(Kyushu Institute of Technology) |
| Date | 2024-03-14 |
| Paper # | SIS2023-48 |
| Volume (vol) | vol.123 |
| Number (no) | SIS-440 |
| Page | pp.pp.17-20(SIS), |
| #Pages | 4 |
| Date of Issue | 2024-03-07 (SIS) |