, which will be held in Beijing, 7-10 November 2024. We invite researchers, practitioners, and industry experts to submit their papers and share their latest findings in this rapidly evolving field.
The special session paper
submission deadline is July 30, 2024. Prospective authors are invited to submit full-length, five-page papers (the fifth page may contain only references). You can visit the
ISCSLP 2024 website and the
Special Session page for more information and paper submission details.
We look forward to your participation!
Best regards,
Longbiao Cheng
On behalf of the Organizing Committee:
Andong Li, Tencent AI Lab
Longbiao Cheng, Institute of Neuroinformatics, University of Zurich and ETH Zurich
Junfeng Li, Institute of Acoustics, Chinese Academy of Sciences
Chengshi Zheng, Institute of Acoustics, Chinese Academy of Sciences
---------------------------------------------
The ISCSLP is a biennial conference that brings together scientists, researchers, and practitioners to discuss the latest progress in all theoretical and technological aspects of spoken language processing. It is scheduled to take turns running the event in four Chinese-spoken regions, namely, Singapore, Mainland China, Taiwan, and Hong Kong. The first ISCSLP took place in Singapore in 1998. Since then, it has been successfully held in Beijing (2000), Taipei (2002), Hong Kong (2004), Singapore (2006), Kunming (2008), Tainan (2010), Hong Kong (2012), Singapore (2014), Tianjin (2016), Taipei (2018), Hong Kong (2020) and Singapore (2022).
While ISCSLP is focused primarily on Chinese languages, works on other languages that may be applied to Chinese speech and language are also encouraged. The working language of ISCSLP is English.
About the Special Session:
The advent of virtual reality (VR) has greatly influenced and changed many fields, such as entertainment, gaming, and online conference. As a critical component of VR experience, digital signal processing plays a vital role in enabling immersive and effective virtual conferences. The special session, titled “Recent advances in speech processing and binaural signal processing for VR conference”, aims to gather experts, researchers, and practitioners from both academia and industrial fields in the field of speech processing, spatial audio rendering, and human-computer interaction to discuss and explore the state-of-the-art developments that enhance VR conferencing experiences. The significance of this topic stems from the increasing need for advanced remote collaboration tools, a demand that has been amplified by the previous global pandemic. By boosting innovation in speech processing and binaural signal processing for VR, we can promote more engaging and productive virtual conferences, ultimately benefiting numerous industries and sectors.
This special session is intended to provide a platform for knowledge exchange, idea generation, and collaboration opportunities among researchers and industry professionals. This session will showcase cutting-edge research in speech processing and binaural signal processing for VR conference and inspire further advancements in the rapidly evolving domain.
The research scope for this special session includes, but is not limited to:
1. Spatial audio and 3D sound rendering for immersive VR experiences
2. Advanced speech signal processing techniques for VR conferences
3. Speech enhancement and voice quality improvements in virtual settings
4. Multilingual and multi-speaker support for inclusive VR conferences
5. Machine learning and artificial intelligence applications for speech techniques in VR
6. Evaluation methodologies and metrics for speech technologies in VR conferences
7. Accessibility and assistive technologies for speech-impaired users in VR conferencing
8. Security and ethical challenges in VR conferences using speech technologies
9. User experience (UX) design principles for speech interfaces in VR environments
10. Cognitive and emotional aspects of speech interactions in VR conferences
11. Speech recognition and synthesis in VR conferencing environments