FinVolution Group has officially launched the 2026 FinVolution Global Data Science Competition. This year’s challenge focused on modeling turn-taking in conversations, with the aim of giving voice AI a sense of when to speak.
Voice interactions have reached the age of native audio, with AI responding in real-time. What’s still missing is what humans do instinctively: knowing when to change direction, when to be silent, and when a short “hmm” is the right response. Without this, even the fastest models will talk to the user and stall the interaction.
This year’s participants will be given 30 seconds of dual-channel interaction as context to predict audio events that may occur within the next 800 milliseconds, equipping the AI with the social intuition to read user intent and respond at the right time.
Also read: AIThority interview with Rohit Agarwal, Founder and CEO of Portkey
The dataset behind this challenge is built from real dual-channel phone conversations recorded across 35 regions in China, spanning a wide range of dialects and speech styles. Audio is provided in combination with ASR transcripts and word-level timestamps, allowing participants to build pure audio or multimodal systems.
“For more than a decade, this competition has been our way of connecting academic research with real-world applications,” said Tiezheng Li, CEO of FinVolution Group. “Turn-taking is one of the unsolved problems in voice interaction today. We hope that what we build here will be pervasive far beyond research, allowing millions of users to experience more natural, human-like conversations in their daily lives.”
The 2026 Challenge is supported by the China Computer Federation (CCF) Natural Language Processing Technology Committee as academic advisor, in collaboration with Fudan University Natural Language Processing Laboratory. It is also an official partner competition of the 15th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2026). Top-performing teams will earn a direct path to presenting at NLPCC 2026 with the global NLP research community.
Also read: AI-powered risk intelligence: How financial institutions are anticipating systemic shocks
[To share your insights with us, please write to psen@itechseries.com]
