Shanghai Jiao Tong University Unveils ‘Jiaojiao’ a GPT-4o Rival

作者智能小编

4 月 16, 2025 #speechai, #机器之心

黄山的油菜花

Shanghai, China – In a significant leap for academic research in the field of intelligent voice interaction, Shanghai Jiao Tong University (SJTU) has announced the launch of Jiaojiao, a cutting-edge spoken dialogue and emotion model. This marks a pivotal moment as it is the world’s first purely academic self-developed model capable of supporting real-time multi-person spoken dialogue. Some are even comparing Jiaojiao to OpenAI’s recently released GPT-4o.

Developed by the Auditory Cognition and Computational Acoustics Laboratory at SJTU, Jiaojiao is more than just a smart voice assistant. It is designed to be a versatile conversational partner capable of handling multiple speakers, languages, roles, and emotions.

Key Highlights of Jiaojiao

The Jiaojiao spoken dialogue and emotion model boasts a range of impressive capabilities, setting it apart from existing voice dialogue models:

Multi-Person Dialogue with Seamless Switching: Whether it’s a family gathering, a team meeting, or a casual conversation among friends, Jiaojiao can engage in natural and fluid dialogue with multiple users simultaneously. It can accurately identify each speaker, understand their contributions, and provide personalized responses. Furthermore, it can provide accurate summaries, making conversations more dynamic and efficient.
Global Language Support with Dialect Recognition: Jiaojiao currently supports four major languages: Chinese, English, Japanese, and French. This allows for a wide range of users to interact with the model in their native tongue.

Academic Prowess Meets Real-World Application

The development of Jiaojiao underscores the growing importance of academic research in driving innovation in the field of artificial intelligence. By focusing on real-time multi-person dialogue and emotional understanding, SJTU has created a model that has the potential to revolutionize how we interact with technology.

The launch of Jiaojiao is a testament to the dedication and expertise of the researchers at SJTU’s Auditory Cognition and Computational Acoustics Laboratory. It represents a significant step forward in the development of more natural, intuitive, and emotionally intelligent voice assistants. As AI continues to evolve, models like Jiaojiao will play a crucial role in shaping the future of human-computer interaction.

References: