From September 26th to September 28th, 2025, the "2025 National Conference on Speech, Auditory and Musical Acoustics" was successfully held at Daoyuan Building of the Chinese University of Hong Kong, Shenzhen, with the theme "Intelligent Speech, Auditory Perception, and Music Acoustics: Cross-Integration and Future Trends".

4 parallel sessions were held during the conference, including Frontiers in Intelligent Speech Technology, Psychoacoustics and Auditory Enhancement Technology, Music Acoustics Theory and Technology and Intelligent Acoustics and Interdisciplinary Applications. At the conference, a total of 7 plenary invited lectures and 19 thematic reports were delivered, with over 150 participants in attendance. Meanwhile, it also attracted four enterprises such as Hygon, HOLLYLAND, Huahon Date Technology, and Inspur to participate in.

The conference focused on the basic theories, technological innovations, application development and cutting-edge trends in Speech, Auditory Science, Musical Acoustics, and their related interdisciplinary fields. It builds a communication platform for experts and scholars from universities, research institutions, enterprises, and public institutions engaged in scientific research, technological development and teaching practice in this field, and is committed to promoting academic progress and achievement transformation in the fields of Speech, Auditory science, Musical Acoustics in China.

The conference was hosted by the Speech, Audition and Music Acoustics Branch of the Acoustical Society of China, and the Speech and Intelligent Information Processing Laboratory of the Institute of Acoustics, Chinese Academy of Sciences. It was organized by The Chinese University of Hong Kong, Shenzhen, Shenzhen University, Southern University of Science and Technology  and Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, with co-organization by School of Artificial Intelligence, CUHK-Shenzhen. 

Opening Ceremony

The opening ceremony of the conference was hosted by Professor Zhizheng WU, a professor from the School of Artificial Intelligence, CUHK-Shenzhen and an expert in the fields of Speech Interaction, Speech Generation, and Audio Authentication. Researcher Jun YANG, Vice President of the Acoustical Society of China and Deputy Director of the Institute of Acoustics, Chinese Academy of Sciences. Researcher Yan Yonghong, Chief Scientist of IOA, CAS. Academician Haizhou LI, Dean of School of Artificial Intelligence and X.Q. Deng Presidential Chair Professor. And Researcher Junfeng LI from IOA, CAS delivered speeches respectively.

In his speech, Researcher Jun YANG emphasized that the field of acoustics—particularly its intersection with AI—functions as a technological bridge for human-computer interaction and also stands as a vital carrier of musical civilization. He expressed the hope that more graduates and young scholars will dedicate themselves to scientific research and contribute to the inheritance of spiritual civilization through technological advancement.

In his speech, Researcher Yonghong YAN affirmed the rapid development of the artificial intelligence (AI) industry and its trait of keeping pace with the times, and finally conveyed earnest expectations to the younger generation of scholars.

In his speech, Academician Haizhou LI pointed out that the difference between modern acoustics and traditional acoustics lies in its integration with AI. He clearly identified the key improvement directions that the industry urgently needs to break through, and at the same time, combined with his own experience, emphasized the importance of interest and passion for scientific research.

Finally, Researcher Junfeng LI from the Institute of Acoustics, Chinese Academy of Sciences expressed his gratitude to the guests, organizers, and co-organizers of this conference, and introduced the agenda and main content of the conference.

Researcher Jun YANG, Vice President of the Acoustical Society of China and Deputy Director of the Institute of Acoustics, CAS

Researcher Yonghong YAN, Chief Scientist of the Institute of Acoustics, CAS

Academician Haizhou LI, Dean of SAI and X.Q. Deng Presidential Chair Professor

Researcher Junfeng LI from the Institute of Acoustics, CAS

 Plenary Invited Lectures

The conference meticulously organized the plenary invited lecture session, specially inviting 7 senior domestic experts in speech, auditory, and musical acoustics-related fields to deliver plenary lectures that balance depth and breadth. This session was chaired by Academician Haizhou LI, Dean of SAI and X.Q. Deng Presidential Chair Professor at CUHK-Shenzhen.

Plenary Invited Lecture 1

Researcher Jun YANG, Vice President of the Acoustical Society of China and Deputy Director of the Institute of Acoustics, CAS, delivered an invited lecture on Acoustics themed "Advances and Applications of New Electroacoustic Technology Under the Trend of Intelligence".

 Jun YANG, Vice President of the Acoustical Society of China and Deputy Director of the Institute of Acoustics, CAS

Plenary Invited Lecture 2

Professor Ningyu WANG, Vice Dean of the School of Otorhinolaryngology at Capital Medical University, delivered an invited lecture on the research and development of SL series sound source localization-related products, themed "Clinical-Basic-Translational-Clinical: Sharing on the R&D of SL Series Products".

 Professor Ningyu WANG, Vice Dean of the School of Otorhinolaryngology at Capital Medical University

Plenary Invited Lecture 3

Professor Deliang WANG  from CUHK-Shenzhen delivered an invited lecture related to Audiovisual Systems, with the theme "AV-CrossNet: An Audiovisual Complex Spectral Mapping Network for Speech Separation".

Professor Deliang WANG from CUHK-Shenzhen

Plenary Invited Lecture 4

Professor Xiaodong FU from the China Conservatory of Music delivered an invited lecture on Acoustics, with the theme "Quantitative Research on the Acoustic Characteristics of National Orchestras — Acoustic Interpretation of 'Sharp, Flat, Chaotic, Noisy'".

Professor Xiaodong FU from the China Conservatory of Music

Plenary Invited Lecture 5

Professor Changcai LONG from Huazhong University of Science and Technology delivered an invited lecture related to Auditory Science, with the theme "Mechanism of Cochlear Information Processing: Revealing Tone Perception in Cochlear Implants and Strategies for Enhancing Speech Intelligibility in Hearing Aids".

Professor Changcai LONG from Huazhong University of Science and Technology

Plenary Invited Lecture 6

Professor Jianguo WEI from Tianjin University delivered an invited lecture related to Speech, with the theme "Observation and Modeling Research on Articulatory Mechanisms for Personalized Speech".

Professor Jianguo WEI from Tianjin University

Plenary Invited Lecture 7

Lan WANG from the Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences delivered an invited lecture related to Speech, with the theme "Speech Disorder Rehabilitation Based on Brain-Inspired Intelligence".

Lan WANG from the Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

Symposium Reports

In addition, this conference featured a key symposium report session. A number of domestic experts in relevant research fields focused on areas such as Speech, Auditory and Musical Acoustics, and delivered symposium reports of the conference with detailed content as well as in-depth perspectives.

Symposium Report 1

Professor Jing LU from Nanjing University delivered a symposium report related to Auditory Science, with the theme "Advances in Intelligent Audio Technology for Auditory Enhancement".

Professor Jing LU from Nanjing University

Symposium Report 2

Professor Yanmin QIAN from Shanghai Jiao Tong University delivered a symposium report related to Auditory Science, with the theme "Latest Advances in Auditory Cognition and Computational Acoustics".

Professor Yanmin QIAN from Shanghai Jiao Tong University

Symposium Report 3

Professor Gongping HUANG from Wuhan University delivered a symposium report related to Speech, with the theme "High-Fidelity Beamforming Speech Enhancement for Microphone Arrays".

Professor Gongping HUANG from Wuhan University 

Symposium Report 4

Yating YANG from the Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences delivered a symposium report related to Multilingual Cross-Modal Research, with the theme "Unified Representation of Multilingual Cross-Modal Data and Intelligent Information Sorting".

 Yating YANG from the Xinjiang Technical Institute of Physics and Chemistry, (CAS)

Symposium Report 5

Associate Professor Huijun DING from Shenzhen University delivered a symposium report related to the field of Speech and Communication Disorders, with the theme "New Advances in Rehabilitation Technology for Speech and Communication Disorders".

Associate Professor Huijun DING from Shenzhen University

Symposium Report 6

Lecturer Zhaorui LIU from Xi'an Conservatory of Music delivered a symposium report on Acoustics, with the theme "Application and Practice of Musical Acoustics Technology in Art Exhibitions".

Lecturer Zhaorui LIU from Xi'an Conservatory of Music

Symposium Report 7

Associate Professor Ailin ZHANG from Shenzhen University delivered a symposium report on Acoustics, with the theme "Visible Acoustics: Vibration of Bowed String Instruments".

Associate Professor Ailin ZHANG from Shenzhen University

Symposium Report 8

Assistant Professor Yaolong JU from Greater Bay Area University delivered a symposium report related to Musical Acoustics, with the theme "Multimodal Music Transcription and Its Applications".

Assistant Professor Yaolong JU from Greater Bay Area University

Symposium Report 9

Associate Professor Rongfeng LI from Beijing University of Posts and Telecommunications (BUPT) delivered a symposium report related to Musical Acoustics, with the theme "The Renaissance of Expert Systems — Artificial Intelligence in Traditional Chinese Musical Instruments".

Associate Professor Rongfeng LI from Beijing University

Symposium Report 10

Associate Yan GAO from the Central Conservatory of Music delivered a symposium report related to Musical Acoustics, with the theme "Quantitative Research on Musical Aesthetics: From Folk Music Databases to Cross-Modal Audiovisual Interaction".

Associate Yan GAO from the Central Conservatory of Music

Symposium Report 11

Professor Lan TIAN from Shandong University delivered a symposium report related to Auditory Science, with the theme "Fine Time-Frequency Coding of Cochlear Implants and Objective Quantitative Decoding Prediction of Auditory Function Based on Brain-Inspired Intelligence".

Professor Lan TIAN from Shandong University

Symposium Report 12

Associate Professor Nengheng ZHENG from Shenzhen University delivered a symposium report related to Auditory Science, with the theme "The Influence of Frequency Resolution on Auditory Perception in Cochlear Implants and Exploration of Strategies".

Associate Professor Nengheng ZHENG from Shenzhen University 

Symposium Report 13

Associate Researcher Dingding YAO from the Institute of Acoustics, Chinese Academy of Sciences delivered a symposium report related to Auditory Science, with the theme "Research Progress on Binaural Virtual Auditory Reproduction Technology".

Associate Researcher Dingding YAO from the Institute of Acoustics, IACAS

Symposium Report 14

Associate Professor Honglin CAO from China University of Political Science and Law delivered a symposium report related to Speech, with the theme "Construction of a Forensic Speech Identification Platform Based on Large-Scale Speech Databases".

Associate Professor Honglin CAO from CUPL

Symposium Report 15

Professor Zhigang CHU from Chongqing University delivered a symposium report related to Acoustics, with the theme "Quantitative Trade-off of Sound Field Zoning Performance Based on Acoustic Contrast Control".

Professor Zhigang CHU from Chongqing University

Symposium Report 16

Professor Ming LI from Duke Kunshan University delivered a symposium report related to Acoustics, with the theme "Research Progress on Machine Abnormal Sound Detection: From Discriminative Modeling to Pre-trained Frameworks and Application Exploration".

Professor Ming LI from Duke Kunshan University

Symposium Report 17

Professor Zhizheng WU from School of Artificial Intelligence, CUHK-Shenzhen, an expert in the fields of Speech Interaction, Speech Generation and Audio Authenticity Verification, delivered a symposium report related to speech and acoustics, with the theme "Generative Speech and Singing Voice Enhancement".

Professor Zhizheng WU from SAI at CUHK-Shenzhen

Symposium Report 18

Professor Ling Zhenhua from the University of Science and Technology of China (USTC) delivered a symposium report related to Speech, with the theme "Personalized Speech Generation Based on Multimodal Timbre Description".

Symposium Report 19

Professor Axu HU from Northwest Minzu University delivered a symposium report related to Speech and Acoustics, with the theme "Acoustic and Physiological Research on the Pronunciation Mechanism of Mongolian Khoomei".

Closing Ceremony

With the conclusion of the closing ceremony, the "2025 National Conference on Speech, Audition and Music Acoustics" has come to a successful end. At the closing ceremony, the host, Researcher Junfeng LI, delivered a comprehensive summary of the conference’s reporting achievements. This three-day event was not only an academic discussion and achievement-sharing occasion but also a collision of ideas spanning the fields of humanities, art, and technology, laying a solid foundation for the future development of speech, audition, and music acoustics.

While this academic gala has drawn to a close, the journey of academic exploration into "Intelligent Speech, Auditory Perception, and Music Acoustics" will never cease. Let us look forward to our next gathering and continue to pen a new academic chapter in the fields of Speech, Auditory Perception and Music Acoustics!