个人简介

张景宣，2016年本科毕业于中国科学技术大学少年班学院，电子信息工程专业。2021年毕业于中国科学技术大学，获得信息与通信工程专业博士学位。2020年在英国爱丁堡大学语音研究中心进行联合培养。2021年至2023年在中国科学技术大学和科大讯飞联合博士后工作站工作。2023年7月起担任伟德bevictor中文版讲师。在语音领域高水平国际会议ICASSP、INTERSPEECH和国际期刊IEEE/ACM TASLP等上已发表十余篇论文。研究方向包括多模态语音处理、语音识别、语音生成、语音无监督预训练等。

详细信息请访问我的个人网站：https://jxzhanggg.github.io/online-cv

学术论文

[1] Jing-Xuan Zhang, Genshun Wan, Jianqing Gao, Zhen-Hua Ling, “Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models”, Pattern Recognition, vol. 162, pp. 1-11, 2025

[2] Jing-Xuan Zhang, Tingzhi Mao, Longjiang Guo, Jin Li, Lichen Zhang, “Target speaker lipreading by audio–visual self-distillation pretraining and speaker adaptation”, Expert Systems with Applications, vol. 272, pp. 1-12, 2025

[3] Jing-Xuan Zhang, Genshun Wan, Zhen-Hua Ling, Jia Pan, Jianqing Gao, Cong Liu, “Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation”, IEEE ICASSP, pp. 1-5, 2023

[4] Jing-Xuan Zhang, Genshun Wan, Jia Pan, “Is Lip-Region-of-Interest Sufficient for Lipreading?”, ACM ICMI, pp. 1-5, 2022

[5] Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai, “Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations”, IEEE/ACM Transaction on Audio, Speech and Lang, vol. 28, no. 1, pp. 540-552, 2020

[6] Jing-Xuan Zhang, Zhen-Hua Ling, Li-Juan Liu, Yuan Jiang, Li-Rong Dai,“Sequence-to-Sequence Acoustic Modeling for Voice Conversion”, IEEE/ACM Trans. on Audio, Speech and Lang, vol. 27, no. 3, pp. 631-644, 2019

[7] Jing-Xuan Zhang, Korin Richmond, Zhen-Hua Ling, Li-Rong Dai, “TaLNet: Voice Reconstruction from Tongue and Lip Articulation with Transfer Learning from Text-to-Speech Synthesis”, Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), pp. 14402-14410, 2021

[8] Jing-Xuan Zhang, Zhen-Hua Ling, Yuan Jiang, Li-Juan Liu, Chen Liang, Li-Rong Dai, “Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision”, IEEE ICASSP, pp. 6785-6789, 2019

[9] Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai, “Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis”, IEEE ICASSP, pp. 4789-4793, 2018

[10] Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai, “Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning”, INTERSPEECH, pp. 771-775, 2020

[11] Jing-Xuan Zhang, Li-Juan Liu,Yan-Nian Chen, Ya-Jun Hu, Yuan Jiang, Zhen-Hua Ling, Li-Rong Dai, “Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer”, Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge, pp. 121-125, 2020

发表专利

[1] 张景宣，万根顺，付中华，潘嘉，高建清，刘聪，胡国平，刘庆峰,“一种预训练方法及相关方法和设备”，2023-4-19, 中国, CN202310093381.1

[2] 张景宣，万根顺，潘嘉，刘聪，胡国平，刘庆峰，付中华，“多模态语音识别方法、装置、设备及存储介质”, 2022-9-21, 中国, CN202211150783.2

[3] 张景宣，万根顺，高建清，刘聪，胡国平，刘庆峰，胡郁，“语音识别方法、语音识别设备及计算机可读存储介质”, 2022-4-5, 中国, CN202210400143.6

[4] 张景宣, 万根顺, 高建清, 刘聪, 胡国平, 刘庆峰, “语音识别方法、语音识别模型的训练方法以及相关装置”, 中华人民共和国国家知识产权局, 发明专利, 2022-5-17, CN202111666006.9

[5] 张景宣,万根顺,付中华,潘嘉,高建清,刘聪,胡国平,刘庆峰,“视频信号处理方法、装置、设备及可读存储介质”, 2022-12-8, 中国, CN202211570582.8

科研项目

[1] 开放世界下鲁棒性的音视频语音识别研究，国家自然科学基金委，青年科学基金项目，在研，主持，2025.01 - 2027.12

[2] 据稀疏条件下的个性化多模态语音识别研究，中央高校基本科研业务费专项，青年教师自由探索项目，在研，主持，2025.01 - 2026.12

[3] 基于大规模无监督预训练的语音表征提取方法研究与应用，陕西省科技厅，重点产业创新链项目，结项，主持，2023.01 - 2024.12