Chinese Multi-Dialect Speech Recognition Challenge
This challenge focuses on Chinese multi-dialect speech recognition and dialect identification, providing a unified evaluation dataset, metrics, and competition pipeline to offer the research community and industry an open, fair, and reproducible benchmark for Chinese multi-dialect speech processing.
This session invites discussion on auditory perception and human-robot interaction of intelligent agents in commercial exhibition, home companionship, and industrial collaboration scenarios, covering sound event recognition, spatial localization, auditory scene analysis, multi-speaker recognition, emotional speech synthesis, and other frontier directions.
We invite proposals for special sessions from universities, research institutions, and enterprises worldwide. Various formats are supported, including frontier topic submissions, expert discussions, institutional research showcases, and competitions, to build a diverse, open, and high-level academic exchange platform.
Stay Tuned
We are preparing more exciting frontier academic sessions and competitions. Stay tuned. If you are interested in organizing a special session, please submit your proposal through the "Call for Special Sessions" channel above.