中国科学院声学研究所研究员、中国科学院大学岗位教授、博士生导师；国家杰出青年基金获得者、优秀青年基金获得者、中国科学院人才计划入选者。

    主要从事音频信号处理与智能声学基础理论及应用的研究工作，先后主持国家自然科学基金杰青、优青、领域基金重点项目、后勤开放课题等；解决了制约声学在若干场景中应用的难题，服务于国家重大战略需求。

081002-信号与信息处理

语音信号处理、3D听觉技术、深度学习在语音信号处理中的应用

   

2009-10~现在, 中国科学院声学研究所, 研究员

2014-06-30-2020-12-31,IEICE Trans. Fundamental, Editor
2014-01-01-今,Speech Communication, Subject Editor
2009-05-31-2016-12-31,Journal of Recent Patents on Signal Processing, 编委

语音信号处理
本科生毕业设计（电子信息工程）

   

（1） 基于麦克风阵列和后滤波技术的噪声处理技术研究, 一等奖, 其他, 2012
（2） 助听器双耳语音增强技术, 一等奖, 其他, 2007
（3） 两输入-两输出语音增强技术, 一等奖, 其他, 2006

[1] 姚鼎鼎, 赵佳乐, 李军锋, 颜永红. 一种头相关传输函数的预测方法、装置和电子设备. CN: CN114067832A, 2022-02-18.

[2] 李军锋, 陈道成, 姚鼎鼎, 颜永红. 一种主动噪声消除方法、装置、电子设备和存储介质. CN: CN113889068A, 2022-01-04.

[3] 李军锋, 顾建军, 颜永红. 一种残余回声及噪声消除方法及装置. CN: CN112863535A, 2021-05-28.

[4] 李军锋, 孙兴伟, 颜永红. 混响语音的混响抑制方法及装置. CN: CN112687284A, 2021-04-20.

[5] 栾书明, 李军锋, 颜永红. 一种声学回波消除与去混响方法及装置. CN: CN111768796A, 2020-10-13.

[6] 李军锋, 程龙彪, 夏日升, 颜永红. 一种基于深度学习的双通道声源定位方法. CN: CN111239686B, 2021-12-21.

[7] 李军锋, 尹路, 颜永红. 一种基于深度学习降低MFCC特征失真的语音增强方法. CN: CN111243617A, 2020-06-05.

[8] 李军锋, 宋思远, 颜永红. 一种多通道远场语音增强方法. CN: CN111081267A, 2020-04-28.

[9] 李军锋, 尹路, 颜永红. 一种基于深度学习的多人语音分离方法. CN: CN109584903A, 2019-04-05.

[10] 李军锋, 孙兴伟, 夏日升, 颜永红. 一种基于深度学习的双耳语音增强方法. CN: CN109448751A, 2019-03-08.

[11] 夏日升, 姚鼎鼎, 李军锋, 颜永红. 一种声源高度角控制方法和系统. CN: CN109637550A, 2019-04-16.

[12] 李军锋, 高飞, 颜永红. 一种提升远场语音识别的前端处理方法和系统. CN: CN109523999A, 2019-03-26.

[13] 李军锋, 李煦, 颜永红. 一种无监督单传声器语音降噪方法及系统. CN: CN108574911A, 2018-09-25.

[14] 李军锋, 李煦, 颜永红. 一种基于性别融合信息的语音降噪方法. CN: CN108573698A, 2018-09-25.

[15] 李军锋, 李煦, 颜永红. 一种基于NMF算法的单传声器语音分离方法. CN: CN108573711A, 2018-09-25.

[16] 李军锋, 孙兴伟, 杨磊, 王立众, 夏日升. 一种5-2通道音频转换优化方法. CN: CN107968984A, 2018-04-27.

[17] 李军锋, 房倩倩, 夏日升, 颜永红. 基于人耳听觉特性的音频重放系统均衡方法. CN: CN106559722A, 2017-04-05.

[18] 夏日升, 李军锋, 颜永红. 一种串声消除滤波器的生成方法及三维声音重放方法. CN: CN105792075A, 2016-07-20.

[19] 应冬文, 李军锋, 冯永强, 潘接林, 颜永红. 一种基于支配相关的多稀疏声源定位方法. CN: CN105403860A, 2016-03-16.

[20] 李军锋, 夏日升, 颜永红. 一种房间混响合成方法. CN: CN104703111A, 2015-06-10.

[21] 应冬文, 李军锋, 冯永强, 潘接林, 颜永红. 一种声源定位方法及装置. CN: CN103076593B, 2014-09-10.

[22] 应冬文, 李军锋, 冯永强, 潘接林, 颜永红. 一种声源定位方法及装置. CN: CN103076593A, 2013-05-01.

[23] 李军锋, 夏日升, 付强, 颜永红. 一种基于耳机的虚拟3D重放方法. CN: CN102665156A, 2012-09-12.

[24] 应冬文, 颜永红, 付强, 潘接林, 李军锋. 一种噪声功率谱估计与语音活动性检测方法. CN: CN102800322A, 2012-11-28.

[25] 李军锋, 李娟, 付强, 颜永红. 一种三维声场合成中的距离感合成方法. CN: CN102790931A, 2012-11-21.

[26] 颜永红, 周瑜, 孙艳庆, 李军锋. 一种用于语音情感识别的语音情感特征提取方法. CN: CN101930733A, 2010-12-29.

[27] 姚鼎鼎, 赵佳乐, 李军锋, 颜永红. 一种基于听觉感知特性的头相关传输函数客观评价方法及系统. CN: CN117979218A, 2024-05-03.

[28] 姚鼎鼎, 赵佳乐, 李军锋, 颜永红. 一种个性化头相关传输函数预测方法及系统. 202311520131.8, 2023-11-15.

[29] 姚鼎鼎, 赵佳乐, 李军锋, 颜永红. 一种个性化头相关传输函数预测方法及系统. CN: CN117372624A, 2024-01-09.

[30] 姚鼎鼎, 赵佳乐, 李军锋, 颜永红. 基于稀疏测量的个性化头相关传输函数预测方法及装置. CN: CN116506795A, 2023-07-28.

[31] 姚鼎鼎, 阮小园, 李军锋, 颜永红. 一种耳机虚拟声像头外化方法. CN: CN116456264A, 2023-07-18.

[32] 李军锋, 王洋洋, 颜永红. 一种语音增强方法. CN: CN114581832A, 2022-06-03.

[33] 李军锋, 程龙彪, 姚鼎鼎, 顾建军, 颜永红. 一种目标语音信号的干扰信号生成方法及装置. CN: CN114337908B, 2024-04-12.

[34] 李军锋, 程龙彪, 姚鼎鼎, 顾建军, 颜永红. 一种目标语音信号的干扰信号生成方法及装置. CN: CN114337908A, 2022-04-12.

[35] 栾书明, 李军锋, 颜永红. 一种声学回波消除与去混响方法及装置. CN: CN111768796B, 2024-05-03.

   

[1] Yuan Xie, Jiawei Ren, 李军锋, Ji Xu. Advancing robust underwater acoustic target recognition through multitask learning and multi-gate mixture experts. J. Acoust. Soc. Am.[J]. 2024, 第 3 作者156(null): 244-255, 
[2] Jianjun Gu, Dingding Yao, Junfeng Li, Yonghong Yan. A novel semi-blind source separation framework towards maximum signal-to-interference ratio. SIGNAL PROCESSING[J]. 2024, 第 3 作者  通讯作者  217: http://dx.doi.org/10.1016/j.sigpro.2023.109359.
[3] Yuan Xie, Ji Xu, Jiawei Ren, 李军锋. Adversarial multi-task underwater acoustic target recognition: Toward robustness against various influential factors. J. Acoust. Soc. Am.[J]. 2024, 第 4 作者156(null): 299-313, 
[4] The Journal of the Acoustical Society of America. 2024, 第 8 作者  通讯作者  
[5] Applied Acoustics. 2024,   通讯作者  
[6] The Journal of the Acoustical Society of America. 2024,   通讯作者  
[7] Jianjun Gu, Dingding Yao, Junfeng Li, Yonghong Yan. Scale-certainty geometrically constrained independent vector analysis for determined blind source separation. APPLIED ACOUSTICS[J]. 2023, 第 3 作者  通讯作者  206: http://dx.doi.org/10.1016/j.apacoust.2023.109313.
[8] Kuang, Kelan, Yang, Feiran, Li, Junfeng, Yang, Jun. Three-stage hybrid neural beamformer for multi-channel speech enhancement. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2023, 第 3 作者153(6): 3378-3389, http://dx.doi.org/10.1121/10.0019802.
[9] Jianjun Gu, Longbiao Cheng, Dingding Yao, Junfeng Li, Yonghong Yan. The effect of source sparsity on independent vector analysis for blind source separation. SIGNAL PROCESSING[J]. 2023, 第 4 作者  通讯作者  213: http://dx.doi.org/10.1016/j.sigpro.2023.109199.
[10] Daocheng Chen, Dingding Yao, Jianjun Gu, Junfeng Li, Yonghong Yan. Further investigation of horizontal sound localization in noise. INTER-NOISE 2023. 2023, 第 4 作者
[11] Zelin Qiu, Jianjun Gu, Dingding Yao, Junfeng Li. Exploring Auditory Attention Decoding using Speaker Features. INTERSPEECH 2023. 2023, 第 4 作者
[12] 柳宗铭, 王丽, 李军锋, 张鹏远. 声学发音模型辅助建模的发音错误检测与诊断. 声学学报[J]. 2023, 第 3 作者48(1): 264-273, http://lib.cqvip.com/Qikan/Article/Detail?id=7108828889.
[13] Qiu, Zelin, Gu, Jianjun, Yao, Dingding, Li, Junfeng, Yan, Yonghong. TF-NSSE: A time-frequency domain neuro-steered speaker extractor. APPLIED ACOUSTICS[J]. 2023, 第 4 作者  通讯作者  211(null): http://dx.doi.org/10.1016/j.apacoust.2023.109519.
[14] Applied Acoustics. 2023,   通讯作者  
[15] Dingding Yao, Jiale Zhao, Longbiao Cheng, Junfeng Li, Xiaodong Li, Yonghong Yan. An individualization approach for head-related transfer function in arbitrary directions based on deep learning. The Journal of the Acoustical Society of America Express Letters[J]. 2022, 第 4 作者2(6): 064401-1, 
[16] Chen, Daocheng, Cheng, Longbiao, Yao, Dingding, Li, Junfeng, Yan, Yonghong. A Secondary Path-Decoupled Active Noise Control Algorithm Based on Deep Learning. IEEE SIGNAL PROCESSING LETTERS[J]. 2022, 第 4 作者  通讯作者  29: 234-238, http://dx.doi.org/10.1109/LSP.2021.3130023.
[17] Cheng, Longbiao, Sun, Xingwei, Yao, Dingding, Li, Junfeng, Yan, Yonghong. Estimation Reliability Function Assisted Sound Source Localization With Enhanced Steering Vector Phase Difference. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING[J]. 2021, 第 4 作者  通讯作者  29(无): 421-435, http://dx.doi.org/10.1109/TASLP.2020.3043107.
[18] 李军锋. 结合卷积神经网络与混响时间注意力机制的混响抑制. 声学学报. 2021, 第 1 作者  通讯作者  
[19] Li, Junfeng, Wu, Biao, Yao, Dingding, Yan, Yonghong. A mixed-order modeling approach for head-related transfer function in the spherical harmonic domain. APPLIED ACOUSTICS[J]. 2021, 第 1 作者  通讯作者  176: http://dx.doi.org/10.1016/j.apacoust.2020.107828.
[20] Song, Siyuan, Cheng, Longbiao, Luan, Shuming, Yao, Dingding, Li, Junfeng, Yan, Yonghong. An integrated multi-channel approach for joint noise reduction and dereverberation. APPLIED ACOUSTICS[J]. 2021, 第 5 作者  通讯作者  171: http://dx.doi.org/10.1016/j.apacoust.2020.107526.
[21] Cheng, Longbiao, Li, Junfeng, Yan, Yonghong. FSCNet: Feature-Specific Convolution Neural Network for Real-Time Speech Enhancement. IEEE SIGNAL PROCESSING LETTERS[J]. 2021, 第 2 作者  通讯作者  28(无): 1958-1962, http://dx.doi.org/10.1109/LSP.2021.3113604.
[22] 姚鼎鼎, 徐华兴, 李军锋, 夏日升, 颜永红. Binaural rendering technology over loudspeakers and headphones. ACOUSTICAL SCIENCE AND TECHNOLOGY(AST)[J]. 2020, 第 3 作者  通讯作者  41(1): 134-141, 
[23] Junfeng Li. Improving generative adversarial networks for speech enhancement through regularization of latent representation. Speech Communication. 2020, 第 1 作者  通讯作者  
[24] Yang, Fan, Wang, Ziteng, Li, Junfeng, Xia, Risheng, Yan, Yonghong. Improving generative adversarial networks for speech enhancement through regularization of latent representations. SPEECH COMMUNICATION[J]. 2020, 第 3 作者  通讯作者  118: 1-9, http://dx.doi.org/10.1016/j.specom.2020.02.001.
[25] 王子腾, 孙兴伟, 李军锋, 颜永红. 近似窄带假设下的最小方差无失真响应波束形成. 声学学报[J]. 2020, 第 3 作者45(2): 161-168, https://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFQ&dbname=CJFDLAST2020&filename=XIBA202002002&v=MDE4MTFNclk5RlpvUjhlWDFMdXhZUzdEaDFUM3FUcldNMUZyQ1VSN3FlWitSdkZpamtWNy9CUFNUSmI3RzRITkg=.
[26] Junfeng Li. The role of specral cues in vertical plane elevation perception. Acoustical Science and Technology. 2020, 第 1 作者  通讯作者  
[27] Yin, Lu, Li, Junfeng, Yan, Yonghong, Akagi, Masato. A Two-Stage Phase-Aware Approach for Monaural Multi-Talker Speech Separation. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS[J]. 2020, 第 2 作者  通讯作者  E103D(7): 1732-1743, https://www.webofscience.com/wos/woscc/full-record/WOS:000545550500024.
[28] 栾书明, 程龙彪, 孙兴伟, 李军锋, 颜永红. 基于深度学习的两阶段联合声学回波和混响抑制技术. 信号处理[J]. 2020, 第 4 作者36(6): 948-957, http://lib.cqvip.com/Qikan/Article/Detail?id=7102246945.
[29] Sun, Xingwei, Gao, ZeFeng, Lu, ZhongYi, Li, Junfeng, Yan, Yonghong. A Model Compression Method With Matrix Product Operators for Speech Enhancement. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING[J]. 2020, 第 4 作者  通讯作者  28(1): 2837-2847, http://dx.doi.org/10.1109/TASLP.2020.3030495.
[30] Yao, Dingding, Li, Junfeng, Xu, Huaxing, Xia, Risheng, Yan, Yonghong, IEEE. A SUBBAND ENERGY MODIFICATION METHOD FOR ELEVATION CONTROL IN MEDIAN PLANE. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)[J]. 2019, 第 2 作者586-590, 
[31] 高飞, 黄哲莹, 王子腾, 李军锋, 颜永红. 早晚期混响划分对理想比值掩蔽在语音识别性能上的影响. 声学学报[J]. 2019, 第 4 作者44(4): 788-795, http://lib.cqvip.com/Qikan/Article/Detail?id=7002656332.
[32] Sun, Xingwei, Xia, Risheng, Li, Junfeng, Yan, Yonghong, IEEE. A DEEP LEARNING BASED BINAURAL SPEECH ENHANCEMENT APPROACH WITH SPATIAL CUES PRESERVATION. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). 2019, 第 3 作者5766-5770, http://dx.doi.org/10.1109/icassp.2019.8683589.
[33] Yao, Dingding, Li, Junfeng, Xia, Risheng. A parametric elevation control approach for binaural reproduction. APPLIED ACOUSTICS[J]. 2019, 第 2 作者  通讯作者  148: 360-365, http://dx.doi.org/10.1016/j.apacoust.2018.12.036.
[34] 姚鼎鼎, 李军锋, 夏日升. 一种参数化仰角控制方法. APPLIED ACOUSTICS[J]. 2019, 第 2 作者148(148): 360-365, 
[35] 孙兴伟, 夏日升, 李军锋. A Deep Learning Based Binaural Speech Enhancement Approach with Spatial Cues Preservation. PROC. ICASSP 2019. 2019, 第 3 作者1(1): 
[36] Ziteng Wang, Junfeng Li, Yonghong Yan. Target Speaker Localization Based on the Complex Watson Mixture Model and Time-Frequency Selection Neural Network. APPLIED SCIENCES[J]. 2018, 第 2 作者8(11): 2326, https://doaj.org/article/fdcda42983ec4c19ae2756d41e3b458f.
[37] 李军锋, 徐华兴, 夏日升, 颜永红. 基于听觉感知特性的双耳音频处理技术*. 应用声学[J]. 2018, 第 1 作者37(5): 706-716, http://yysx.cnjournals.cn/ch/reader/view_abstract.aspx?file_no=18Y---03&flag=1.
[38] Li, Yongwei, Li, Junfeng, Akagi, Masato. Contributions of the glottal source and vocal tract cues to emotional vowel perception in the valence-arousal space. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2018, 第 2 作者144(2): 908-916, https://www.webofscience.com/wos/woscc/full-record/WOS:000443620700045.
[39] Wang, Ziteng, Li, Junfeng, Yan, Yonghong. Target Speaker Localization Based on the Complex Watson Mixture Model and Time-Frequency Selection Neural Network. APPLIED SCIENCES-BASEL[J]. 2018, 第 2 作者8(11): https://doaj.org/article/fdcda42983ec4c19ae2756d41e3b458f.
[40] Xu Huaxing, Wang Qia, Xia Risheng, Li Junfeng, Yan Yonghong. A Stochastic Approximation Method with Enhanced Robustness for Crosstalk Cancellation. CHINESE JOURNAL OF ELECTRONICS[J]. 2017, 第 4 作者  通讯作者  26(6): 1269-1275, https://www.webofscience.com/wos/woscc/full-record/WOS:000415662500023.
[41] Xu, Huaxing, Xia, Risheng, Li, Junfeng, Yan, Yonghong. An improved free-field cross-talk cancellation method based on the spherical head model. APPLIED ACOUSTICS[J]. 2017, 第 3 作者  通讯作者  123: 47-54, http://dx.doi.org/10.1016/j.apacoust.2017.03.003.
[42] Ying, Dongwen, Zhou, Ruohua, Li, Junfeng, Yan, Yonghong. Window-Dominant Signal Subspace Methods for Multiple Short-Term Speech Source Localization. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING[J]. 2017, 第 3 作者25(4): 731-744, http://dx.doi.org/10.1109/TASLP.2016.2625458.
[43] 房倩倩, 姚鼎鼎, 李军锋, 夏日升. 基于人耳听觉特性的房间冲激响应多点均衡. 声学技术[J]. 2017, 第 3 作者36(2): 152-156, http://sciencechina.cn/gw.jsp?action=detail.jsp&internal_id=5981691&detailType=1.
[44] Junfeng Li. Window-domain signal processing methods for multiple short-term speech source localization. IEEE/ACM Trans. on Audio, Speech and Language Processing. 2017, 第 1 作者
[45] 许春冬, 张震, 战鸽, 应冬文, 李军锋, 颜永红. 面向语音增强的约束序贯高斯混合模型噪声功率谱估计. 声学学报[J]. 2017, 第 5 作者633-640, 
[46] Sun Xingwei, Xia Risheng, Yang Lei, Wang Lizhong, Li Junfeng, Pan JS, Tsai PW, Huang HC. An improved 5-2 channel downmix algorithm for 3D audio reproduction. ADVANCES IN INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING, VOL 1. 2017, 第 5 作者63: 183-189, 
[47] Junfeng Li. Investigation on advanced audio algorithms architecture for portable devices. The Journal of Audio Engineering Society. 2016, 第 1 作者  通讯作者  
[48] Li Junfeng, Xia Risheng, Fang Qiang, Li Aijun, Yan Yonghong, Lee T, Xie L, Dang J, Wang HM, Wei J, Feng H, Hou Q, Wei Y. Speech Intelligibility Enhancement in Noisy Reverberant Conditions. 201610THINTERNATIONALSYMPOSIUMONCHINESESPOKENLANGUAGEPROCESSINGISCSLP. 2016, 第 1 作者  通讯作者  http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000405610900135.
[49] Trevino, Jorge, Sakamoto, Shuichi, Li, Junfeng, Suzuki, Yoiti. Enhancing Stereo Signals with High-Order Ambisonics Spatial Information. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS[J]. 2016, 第 3 作者  通讯作者  E99D(1): 41-49, http://dx.doi.org/10.1587/transinf.2015MUI0001.
[50] Xu Huaxing, Xia Risheng, Li Junfeng, Yan Yonghong, Rajmic P, Rund F, Schimmel J. A ROBUST STOCHASTIC APPROXIMATION METHOD FOR CROSSTALK CANCELLATION. DAFX 16: 19TH INTERNATIONAL CONFERENCE ON DIGITAL AUDIO EFFECTS. 2016, 第 3 作者93-98, 
[51] Hu, Shichao, Trevino, Jorge, Salvador, Cesar, Sakamoto, Shuichi, Li, Junfeng, Suzuki, Yoiti. A local representation of the head-related transfer function. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2016, 第 5 作者140(3): EL285-EL290, http://dx.doi.org/10.1121/1.4962805.
[52] Cecchi, Stefania, Virgulti, Marco, Primavera, Andrea, Piazza, Francesco, Bettarelli, Ferruccio, Li, Junfeng. Investigation on Audio Algorithms Architecture for Stereo Portable Devices. JOURNAL OF THE AUDIO ENGINEERING SOCIETY[J]. 2016, 第 6 作者  通讯作者  64(1-2): 75-88, https://www.webofscience.com/wos/woscc/full-record/WOS:000371103500007.
[53] 徐华兴, 夏日升, 李军锋, 颜永红. 一种基于物理特性和感知特性的混响模拟方法. 中国科学: 信息科学[J]. 2015, 第 3 作者45(6): 817-826, https://www.sciengine.com/doi/10.1360/N112014-00326.
[54] 许春冬, 王晶, 战鸽, 应冬文, 李军锋, 颜永红. 基于功率谱包络动态分割的鲁棒语音端点检测. 北京理工大学学报[J]. 2015, 第 5 作者35(11): 1189-1193, http://sciencechina.cn/gw.jsp?action=detail.jsp&internal_id=5604624&detailType=1.
[55] Junfeng Li. A spatial extraction method to derive high-order ambisonics data from Stereo sources. Journal of Information Hiding and Multimedia Signal Processing. 2015, 第 1 作者
[56] Xia, Risheng, Li, Junfeng, Primavera, Andrea, Cecchi, Stefania, Suzuki, Yoiti, Yan, Yonghong. A Hybrid Approach for Reverberation Simulation. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES[J]. 2015, 第 2 作者E98A(10): 2101-2108, http://159.226.59.140/handle/311008/2622.
[57] Junfeng Li. Effect of the division of early and late reflections on intelligibility of reverberant noisy speech with binary masking. The Journal of the Acoustical Society of America. 2015, 第 1 作者
[58] Li, Junfeng, Xia, Risheng, Fang, Qiang, Li, Aijun, Pan, Jielin, Yan, Yonghong. Effect of the division between early and late reflections on intelligibility of ideal binary-masked speech. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2015, 第 1 作者  通讯作者  137(5): 2801-2810, https://www.webofscience.com/wos/woscc/full-record/WOS:000354962900033.
[59] 许春冬, 李军锋, 裘嫄, 夏日升, 颜永红. 两扬声器配置下的串声消除系统参数优化设置. 计算机应用[J]. 2014, 第 2 作者5(34): 1503-1506, http://lib.cqvip.com/Qikan/Article/Detail?id=49448871.
[60] Li, Junfeng, Xia, Risheng, Ying, Dongwen, Yan, Yonghong, Akagi, Masato. Investigation of objective measures for intelligibility prediction of noise-reduced speech for Chinese, Japanese, and English. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2014, 第 1 作者  通讯作者  136(6): 3301-3312, https://www.webofscience.com/wos/woscc/full-record/WOS:000345976500043.
[61] ThanhDuc Chau, Li, Junfeng, Akagi, Masato. Binaural Sound Source Localization in Noisy Reverberant Environments Based on Equalization-Cancellation Theory. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES[J]. 2014, 第 2 作者E97A(10): 2011-2020, https://www.webofscience.com/wos/woscc/full-record/WOS:000342784000001.
[62] 许春冬, 夏日升, 应冬文, 李军锋. 面向语音增强的序贯隐马尔可夫模型时频语音存在概率估计. 声学学报[J]. 2014, 第 4 作者39(5): 647-654, https://d.wanfangdata.com.cn/periodical/shengxxb201405015.
[63] Junfeng Li. A sound image externalization approach for headphone reproduction by simulating binaural room impulse response. Chinese Journal of Electronics. 2014, 第 1 作者
[64] Xia Risheng, Li Junfeng, Xu Chundong, Yan Yonghong. A Sound Image Externalization Approach for Headphone Reproduction by Simulating Binaural Room Impulse Responses. CHINESE JOURNAL OF ELECTRONICS[J]. 2014, 第 2 作者23(3): 527-532, https://www.webofscience.com/wos/woscc/full-record/WOS:000339089800018.
[65] Li Junfeng, Xia Risheng, Ying Dongwen, Yan Yonghong, Akagi Masato. Investigation of objective measures for intelligibility prediction of noise-reduced speech for Chinese, Japanese and English,. THE JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2014, 第 1 作者136(6): 3301-3312, 
[66] XIA Risheng, LI Junfeng, XU Chundong, YAN Yonghong. A Sound Image Externalization Approach for Headphone Reproduction by Simulating Binaural Room Impulse Responses. 电子学报：英文版[J]. 2014, 第 2 作者23(3): 527-532, http://lib.cqvip.com/Qikan/Article/Detail?id=662196314.
[67] Primavera, Andrea, Cecchi, Stefania, Li, Junfeng, Piazza, Francesco. Objective and Subjective Investigation on a Novel Method for Digital Reverberator Parameters Estimation. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING[J]. 2014, 第 3 作者22(2): 441-452, https://www.webofscience.com/wos/woscc/full-record/WOS:000332614900014.
[68] Cecchi Stefania, Primavera Andrea, Piazza Francesco, Bettarelli Ferruccio, Li Junfeng, IEEE. Advanced Audio Spatializer combined with a Multipoint Equalization System. PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN). 2014, 第 5 作者3569-3576, 
[69] 颜永红, 李军锋, 应冬文. 语音中元音和辅音的听觉感知研究. 应用声学[J]. 2013, 第 2 作者32(3): 231-236, https://d.wanfangdata.com.cn/periodical/yysx201303011.
[70] Li, Kai, Guo, Yanmeng, Fu, Qiang, Li, Junfeng, Yan, Yonghong. Two-Microphone Noise Reduction Using Spatial Information-Based Spectral Amplitude Estimation. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS[J]. 2012, 第 4 作者E95D(5): 1454-1464, 
[71] Zhou, Yu, Suo, Hongbin, Li, Junfeng, Yan, Yonghong. Harmonic Structure Features for Robust Speaker Diarization. ETRI JOURNAL[J]. 2012, 第 3 作者34(4): 583-590, https://www.webofscience.com/wos/woscc/full-record/WOS:000307423400012.
[72] Junfeng Li. Objective and subjective intelligibility evaluations of noise-reduction algorithms in Mandarin. ACOUSTICS 2012. 2012, 第 1 作者
[73] Li, Junfeng, Yang, Lin, Zhang, Jianping, Yan, Yonghong, Hu, Yi, Akagi, Masato, Loizou, Philipos C. Comparative intelligibility investigation of single-channel noise-reduction algorithms for Chinese, Japanese, and English. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2011, 第 1 作者  通讯作者  129(5): 3291-3301, https://www.webofscience.com/wos/woscc/full-record/WOS:000290450400061.
[74] Li, Junfeng, Sakamoto, Shuichi, Hongo, Satoshi, Akagi, Masato, Suzuki, Yoiti. Two-stage binaural speech enhancement with Wiener filter for high-quality speech communication. SPEECH COMMUNICATION[J]. 2011, 第 1 作者  通讯作者  53(5): 677-689, http://dx.doi.org/10.1016/j.specom.2010.04.009.
[75] Junfeng Li. Integrating meaningful signal extraction for intelligent binaural speech enhancement. Journal of Signal Processing. 2011, 第 1 作者
[76] Zhou, Yu, Li, Junfeng, Sun, Yanqing, Zhang, Jianping, Yan, Yonghong, Akagi, Masato. A Hybrid Speech Emotion Recognition System Based on Spectral and Prosodic Features. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS[J]. 2010, 第 2 作者E93D(10): 2813-2821, http://dx.doi.org/10.1587/transinf.E93.D.2813.
[77] Li, Junfeng, Akagi, Masato. A hybrid microphone array post-filter in a diffuse noise field. APPLIED ACOUSTICS[J]. 2008, 第 1 作者  通讯作者  69(6): 546-557, http://dx.doi.org/10.1016/j.apacoust.2007.01.005.
[78] Li, Junfeng, Sakamoto, Shuichi, Hongo, Satoshi, Akagi, Masato, Suzuki, Yoiti. Adaptive beta-order generalized spectral subtraction for speech enhancement. SIGNAL PROCESSING[J]. 2008, 第 1 作者  通讯作者  88(11): 2764-2776, https://www.webofscience.com/wos/woscc/full-record/WOS:000258813800016.
[79] Li, Junfeng, Akagi, Masato, Suzuki, Yoiti. A two-microphone noise reduction method in highly non-stationary multiple-noise-source environments. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES[J]. 2008, 第 1 作者  通讯作者  E91A(6): 1337-1346, https://www.webofscience.com/wos/woscc/full-record/WOS:000256862800006.
[80] Li, JF, Akagi, M. A noise reduction system based on hybrid noise estimation technique and post-filtering in arbitrary noise environments. SPEECH COMMUNICATION[J]. 2006, 48(2): 111-126, http://dx.doi.org/10.1016/j.specom.2005.06.013.
[81] Junfeng Li, Masato Akagi. Noise reduction method based on generalized subtractive beamformer. MARUZEN COMPANY LTD. 第 1 作者http://oa.las.ac.cn/oainone/service/browseall/read1?ptype=JA&workid=JA201912080715562ZK.
[82] Zelin Qiu, Jianjun Gu, Dingding Yao, Junfeng Li, Yonghong Yan. TF-NSSE: A Time-Frequency Domain Neuro-Steered Speaker Extractor. APPLIED ACOUSTICS. 第 4 作者  通讯作者  http://dx.doi.org/10.1016/j.apacoust.2023.109519.

（1） Noise Reduction Based on Microphone Array and Post-Filtering, Noise Reduction Based on Microphone Array and Post-Filtering, VDM Publishing House Ltd., 2010-06, 第 1 作者

（ 1 ） 语言声学, 负责人, 国家任务, 2025-01--2029-12
（ 2 ） 噪声环境下的3D听觉技术研究, 负责人, 研究所自主部署, 2024-09--2026-08
（ 3 ） 虚拟现实听觉空间定位的机制研究, 参与, 国家任务, 2023-10--2025-10
（ 4 ） XXX3D听觉建模研究, 参与, 国家任务, 2022-10--2024-10
（ 5 ） 多声源场景中听觉注意状态的解码预测模型, 参与, 国家任务, 2022-10--2025-10
（ 6 ） 听觉注意信息介入的语音增强, 参与, 国家任务, 2021-12--2026-11
（ 7 ） XXX研究, 负责人, 国家任务, 2021-10--2024-09
（ 8 ） 发声与言语功能障碍康复训练系统, 负责人, 国家任务, 2021-01--2023-12
（ 9 ） 基于深度学习的声学虚拟现实/增强现实技术, 负责人, 中国科学院计划, 2020-01--2022-12
（ 10 ） XXX研究, 负责人, 国家任务, 2019-08--2021-12
（ 11 ） XXX技术, 负责人, 国家任务, 2019-07--2020-06
（ 12 ） 多语言语音可懂度增强, 负责人, 国家任务, 2018-01--2020-12
（ 13 ） 三维声场的高精度听觉呈现, 负责人, 国家任务, 2017-01--2019-12
（ 14 ） 混响环境下双耳声源定位的研究及应用, 参与, 国家任务, 2017-01--2020-12
（ 15 ） 移动终端三维声场技术, 参与, 国家任务, 2015-01--2017-12
（ 16 ） 互联网环境中文言语信息处理与深度计算的基础理论和方法, 负责人, 国家任务, 2013-01--2017-12
（ 17 ） 面向下一代互联网的超临场感声通信应用研究, 参与, 国家任务, 2011-08--2016-07
（ 18 ） 双耳语音可懂度增强技术研究, 负责人, 国家任务, 2011-01--2013-12
（ 19 ） 语音听感知及其应用研究, 负责人, 中国科学院计划, 2010-08--2014-12

已指导学生

房倩倩  硕士研究生  085208-电子与通信工程  

方向阳  硕士研究生  085208-电子与通信工程  

王琪  博士研究生  081002-信号与信息处理  

姚鼎鼎  博士研究生  081002-信号与信息处理  

高飞  硕士研究生  081002-信号与信息处理  

白海钏  博士研究生  081002-信号与信息处理  

孙兴伟  博士研究生  081002-信号与信息处理  

傅明明  硕士研究生  085208-电子与通信工程  

姚升余  博士研究生  081002-信号与信息处理  

王子腾  博士研究生  081002-信号与信息处理  

尹路  博士研究生  081002-信号与信息处理  

蒿晓阳  硕士研究生  081002-信号与信息处理  

栾书明  硕士研究生  081002-信号与信息处理  

宋思远  硕士研究生  085208-电子与通信工程  

陈道成  博士研究生  081002-信号与信息处理  

高键  硕士研究生  081002-信号与信息处理  

顾建军  博士研究生  081002-信号与信息处理  

王洋洋  硕士研究生  085208-电子与通信工程  

张宇航  硕士研究生  081002-信号与信息处理  

程龙彪  博士研究生  081002-信号与信息处理  

李伟  硕士研究生  085400-电子信息  

阮小园  硕士研究生  085400-电子信息  

现指导学生

王成仲  博士研究生  081002-信号与信息处理  

邱泽林  博士研究生  081002-信号与信息处理  

谢源  博士研究生  081002-信号与信息处理  

冯帆  硕士研究生  085400-电子信息  

赵佳乐  博士研究生  081002-信号与信息处理  

李向前  硕士研究生  081002-信号与信息处理