The book presents selected papers at the 10th Conference on Sound and Music Technology (CSMT) held in June 2023, China. CSMT is a multidisciplinary conference focusing on audio processing and understanding with bias on music and acoustic signals. The primary aim of the conference is to promote the collaboration between art society and technical society in China. In this book, the paper included covers a wide range topic from speech, signal processing, music understanding, machine learning, and signal processing for advanced medical diagnosis and treatment applications, which demonstrates the target of CSMT merging arts and science research together. Its content caters to scholars, researchers, engineers, artists, and education practitioners not only from academia but also industry, who are interested in audio/acoustics analysis signal processing, music, sound, and artificial intelligence (AI).
विषयसूची
A Holistic Evaluation of Piano Sound Quality.- A Survey Of Singing Voice Synthesis.- Double-Mix-Net: A Multimodal Music Emotion Recognition Network with Multi-Layer Feature Mixing.- Research on Generalization of U-Net Intermediate Block Design for Music Source Separation.- XBeat: A Hybrid Cnn-Transformer Model for Beat And Downbeat Tracking.
लेखक के बारे में
Kun Qian (Senior Member, IEEE) received his doctoral degree for his study on automatic general audio signal classification in 2018 in electrical engineering and information technology from Technische Universität München (TUM), Germany. From 2021, he has been appointed to be (Full) Professor at Beijing Institute of Technology, China. He is Senior Member of the IEEE. He was elected as Forbes China “100 Outstanding Overseas Returnees” in 2023. Dr. Qian serves as Associate Editor for the IEEE Transactions on Affective Computing, Frontiers in Digital Health, and BIO Integration. He (co-)authored more than 100 publications in peer-reviewed journals and conference proceedings having received more than 2.4k citations (h-index 30).
Xin Wang is Professor at the School of Music and Recording Arts, Communication University of China, where her research focuses on spatial audio, musical perception, and musical acoustics. She received his doctoral degree of Engineering in Communication and Information Systems from the Communication University of China in 2012. Dr. Wang has presided over ten national and provincial-level scientific research projects, published five books, (co-)authored over forty papers in peer-reviewed journals, and obtained three patents and software copyrights.
Qinglin Meng, Associate Professor, Ph.D., currently works at the Acoustics Laboratory, School of Physics and Optoelectronics, South China University of Technology.
His research focuses on (psycho-)acoustics, signal processing, and information processing to address scientific and technological issues related to hearing health and auditory perception, particularly in areas of technologies of auditory prothesis, especially on cochlear implant coding strategies. He has published articles in reputable academic journals such as JASA, IEEE-TASLP, Hear Res, Trend Hear, and Ear Hear. He is committed to cultivating top talent in hearing health and auditory technology and promoting the development of related industries in China.
Mingzhi Chen is currently Professor at the department of composition of the Xinghai Conservatory of Music, Mentor on its post-graduated programme (Composition and Electronic Music), Chairman of the Music Artificial Intelligence and Sound Technology Council of the Guangdong Sound, Visual, and Lighting Association. His academic focus is on the research and composition of ethnic instrumental music that is interactive with images and physical body movements and theatre sound design. He is the recipient of many prestigious awards including the Government of Japan Agency for Cultural Affairs Award for Stage Arts, Commendation of the International Music Council of UNESCO, and the Artist of the Year Music award from the Hong Kong Arts Development Council in 2018.