
古斌,湖南岳阳人,博士。
一、教育背景与工作经历
2014-2018年,中国科学技术大学电子信息工程专业,本科;
2018-2021年,中国科学技术大学信息与通信工程专业,硕士;
2021-2024年,中国科学技术大学信息与通信工程专业,博士;
2024-至今,中国人民解放军国防科技大学电子科学学院,博士后
二、主要研究领域
语音信号处理、语音识别、说话人识别、音频鉴伪等
三、主持或参与科研项目
1、军委科技委创新特区子课题(Ⅰ、Ⅱ期), XXXX辐射噪声识别,20XX-20XX (参与,技术骨干)
2、招商银行横向课题,文本无关声纹识别防攻击关键技术研究,2022-2023 (参与,技术骨干)
3、自然科学基金委地区重点基金子课题,复杂环境下语音数据的说话人识别及关键词检索,2019-2022 (参与)
4、中国科学院战略先导C类项目,多语种语言对话和理解关键技术,2020-2022 (参与)
四、代表性学术成果
[1] B. Gu, et al, “Memory storable network based feature aggregation for speaker representation learning,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 643–655, 2023, (JCR Q1, Top)
[2] B. Gu, et al, “A dynamic convolution framework for session‐independent speaker embedding learning,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 3647–3658, 2023, (JCR Q1, Top).
[3] B. Gu, et al, “Dynamic convolution with global-local information for session-invariant speaker representation learning,” IEEE Signal Processing Letters, vol. 29, pp. 404–408, 2021, (JCR Q2).
[4] B. Gu, et al, “Deep speaker embedding with frame-constrained training strategy for speaker verification,” in Proceedings of Interspeech, 2022, pp. 1451-1455, (CCF-C,语音旗舰会议).
[5] B. Gu, et al, “An improved deep neural network for modeling speaker characteristics at different temporal scales,” in Proceedings of IEEE ICASSP, 2020, pp. 6814-6818, (CCF-B,语音旗舰会议).
[6] B. Gu, et al, “An adaptive x-vector model for text-independent speaker verification,” in Proceedings of Interspeech, 2020, pp. 1506-1510, (CCF-C,语音旗舰会议).
[7] B. Gu, et al, “Clustering-Based Score Normalization for Speaker Verification,” in Proceedings of IEEE APSIPA ASC, 2019, pp. 553-557.
五、获奖情况
ADD 2023音频鉴伪挑战赛世界第一名
RoboGame 2016 机器人比赛第一名