| DC Field | Value | Language |
|---|
| dc.contributor.author | Chen Zhengyu | - |
| dc.coverage.spatial | Минск | en_US |
| dc.date.accessioned | 2025-09-05T07:45:32Z | - |
| dc.date.available | 2025-09-05T07:45:32Z | - |
| dc.date.issued | 2025 | - |
| dc.identifier.citation | Chen Zhengyu. Software for recognizing speaker by voice / Chen Zhengyu // Информационная безопасность : сборник материалов 61-й научной конференции аспирантов, магистрантов и студентов БГУИР, Минск, 21–25 апреля 2025 г. / Белорусский государственный университет информатики и радиоэлектроники. – Минск, 2025. – С. 13–17. | en_US |
| dc.identifier.uri | https://libeldoc.bsuir.by/handle/123456789/61457 | - |
| dc.description.abstract | . FBank (Filter Bank) is a front-end processing algorithm that processes audio in a way similar to the human ear and extracts features
to improve the performance of speech recognition. The system uses an efficient context-aware masking-based network, CAM++, which uses a
densely connected time-delay neural network (D-TDNN) as the backbone and adopts a novel multi-granularity pooling to capture different levels of
context information.Based on the respective advantages of FBank and CAM++ models, this study designs a software for recognizing speaker by
voice and implements the system through pytorch. | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | БГУИР | en_US |
| dc.subject | материалы конференций | en_US |
| dc.subject | speaker recognition | en_US |
| dc.subject | feature Extraction | en_US |
| dc.subject | neural networks | en_US |
| dc.title | Software for recognizing speaker by voice | en_US |
| Appears in Collections: | Информационная безопасность : материалы 61-й научной конференции аспирантов, магистрантов и студентов (2025)
|
