上海的陆家嘴

【复旦大学研发“眸思”大模型,为视障者打开新“视”界】

复旦大学自然语言处理实验室(FudanNLP)近日传来科技助残的喜讯,由该实验室师生精心研发的多模态大模型“复旦・眸思”(MouSi)成功应用于一款名为“听见世界”的App,为视障人士提供了全新的“看”世界方式。这款创新应用借助一枚普通的摄像头和一对耳机,就能将视觉信息实时转化为语音描述,让视障者能够感知周围环境,实现视觉信息的“听觉化”传递。

“听见世界”App不仅能够准确地将画面内容转述给用户,如描述人物、物体和场景,而且具备智能提示风险的功能,如识别交通信号、障碍物等,大大提升了视障者在日常生活中的行动安全和独立性。这一突破性的技术进展,无疑为视障人群带来了生活的便利和希望,也展示了科技在人文关怀领域的强大潜力。

复旦大学在人工智能与无障碍技术的交叉领域取得的这一成果,不仅体现了科研机构的社会责任感,也彰显了中国在科技普惠上的不懈努力。这款应用的上线,是科技进步与社会福祉的有力结合,预示着更多视障人士将有望享受到科技带来的福祉,更好地融入社会,享受更丰富的生活体验。

来源:IT之家

英语如下:

**News Title:** “Fudan University Develops ‘MouSi’ Model, Enabling Visually Impaired to “Hear” the World”

**Keywords:** MouSi Model, Assistance for the Visually Impaired, Hear the World

**News Content:**

**Fudan University Develops “MouSi” Large Model, Opening a New “Vision” for the Visually Impaired**

Fudan University’s Natural Language Processing Laboratory (FudanNLP) recently announced a groundbreaking advancement in assistive technology, as their multi-modal large model, “Fudan・MouSi,” has been successfully applied to an app named “Hear the World.” This innovative application, using a standard camera and a pair of headphones, transforms visual information into real-time voice descriptions, allowing visually impaired individuals to perceive their surroundings and receive visual information through auditory means.

Not only does the “Hear the World” App accurately narrate the content of the scene, such as describing people, objects, and settings, but it also features a smart risk-alert function, identifying traffic signals and obstacles. This significantly enhances the safety and independence of visually impaired individuals in their daily lives. This breakthrough technology brings convenience and hope to the visually impaired community, demonstrating the immense potential of technology in fostering inclusivity and人文关怀 (humanitarian concern).

Fudan University’s achievement at the intersection of artificial intelligence and accessibility technology underscores the institution’s social responsibility and highlights China’s persistent efforts in promoting technology for all. The launch of this app represents a powerful union of technological progress and societal well-being,预告 (anticipating) that a greater number of visually impaired people will benefit from the fruits of technology, better integrating into society and enjoying a more enriching life experience.

**Source:** IT之家

【来源】https://www.ithome.com/0/753/295.htm

Views: 2

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注