职务职称：

讲师

所属系部：

计算机科学与技术系

研究方向：

智能音频信号处理、声音事件检测

联系电话：

电子邮箱：

ljgao@ujs.edu.cn

个人简介

高利剑，男，江西瑞昌人，博士毕业于江苏大学；2024年10月进入江苏大学计算机科学与通信工程学院工作，主要从事智能音频信号处理、声音事件检测等方向的研究；目前以一作在IEEE/ACM Transactions on Audio, Speech, and Language Processing，ACM International Conference on Multimedia，ICASSP，INTERSPEECH等音频信号处理及人工智能顶级期刊会议上发表论文多篇。

研究方向

（1）智能音频信号处理：围绕声音数据（包括语音信号和非语音信号）利用深度学习等人工智能技术实现对音频内容的理解和分析，例如语音分离、语音增强、语音合成等领域；

（2）声音事件检测：声音事件检测（Sound Event Detection, SED）是音频信号处理领域中的热门研究方向，旨在识别并定位目标声音事件的起止时刻，在音频监控、辅助医疗诊断等方面具有良好的应用价值。

学术服务

[1] 担任IEEE-AMC TASLP, ACM MM, ICME, ICASSP, INTERSPEECH等国际权威期刊和会议审稿人。

[2] 担任NCMMSC 2025（全国人机语音通讯学术会议）程序委员会主席。

课程教学

教研成果

江苏省科学技术奖，三等奖，第五完成人

科研项目

[1]江苏省研究生创新计划项目， 2021-2024，主持，已结题

代表性论著

[1] Lijian Gao, Qirong Mao, and Ming Dong. "On Local Temporal Embedding for Semi-Supervised Sound Event Detection." IEEE/ACM Transactions on Audio, Speech, and Language Processing (2024). (中科院1区, CCF-B)

[2] Lijian Gao, Ling Zhou, Qirong Mao and Ming Dong. "Adaptive hierarchical pooling for weakly-supervised sound event detection." Proceedings of the 30th ACM International Conference on Multimedia (2022). (CPCI, CCF-A)

[3] Lijian Gao, et al. "Reproducibility Companion Paper: On Learning Disentangled Representation for Acoustic Event Detection." Proceedings of the 29th ACM International Conference on Multimedia (2021). (CPCI, CCF-A)

[4] Lijian Gao, Qirong Mao and Ming Dong. “On learning disentangled representation for acoustic event detection.” Proceedings of the 27th ACM International Conference on Multimedia (2019). (CPCI, CCF-A)

[5] Lijian Gao, Qirong Mao and Ming Dong. "Joint-former: Jointly regularized and locally down-sampled conformer for semi-supervised sound event detection." Proceedings of INTERSPEECH (2023). (CPCI, CCF-C)

[6] Qirong MAO, Lijian GAO et. Al. “Weakly-supervised sound event detection method and system based on adaptive hierarchical pooling” US Patent 12,080,319 (PCT专利授权)

[7] Shiyu Yu, Lijian Gao and Qirong Mao. “Global Enhanced Frame Prompt Tuning for Sound Event Detection”. International Conference on Acoustics, Speech, and Signal Processing. (Accepted, 2025). (CPCI, CCF-B)