Speech AI Research center

(人工智慧語音研發中心)

徵人啟示: 誠徵計畫研究助理與工程師

vision (願景)

Long-Term: Universal Human-Machine Interface for Intelligent Entities

In the near future, it's conceivable that humans will communicate directly with intelligent entities using spoken language, instructing them to collaborate. Consequently, next-generation computers and robots will need to not only accurately interpret human language but also possess a deep understanding of world dynamics. Additionally, they should be capable of processing multi-modal information and utilizing various tools, including programming, to execute human commands.

The Future Has Arrived(未來已降臨) !

長期目標：通用智慧機器人口語人機介面

在不久的將來，人類將能直接使用口語與通用智慧機器人進行溝通、指示它們進行合作。所以，下一代的電腦與機器人不僅要能準確解讀人類語言，還必須要能深刻理解世界的運作原理。因此，它們應該具備處理多模態資訊的能力，並利用各種工具來執行人類的命令。

Short-Term: Generative AI & Multi-Modal Foundation Model

We aim to develop robots that can independently learn human language and understand the world by solely watching television. This knowledge will be applied in various fields, such as Smart Medicine, Healthcare, Auto Manufacturing, and Language Tutoring.

短期目標：多模態生成式AI

我們將開發多模態生成式AI，同時處理與生成多種媒體資訊（包括語音、文字、圖片與視訊等等），建立大型多模態基石模型。並將這些模型應用於各個領域，例如機器人、智慧醫療、健康護理、自動化製造和語言教學等等任務。

Members (中心成員)

Function & Operation (中心功能)

Research Areas (研究方向)

Speech Recognition/Synthesis/Translation/Conversion/Enhancement
Speaker/Language/Emotion Recognition
Large Language Models, Multi-Modal (speech, text, image, video) Foundation Model, Intelligent Robots
Embedding System, In-Memory/Storage Computing
Computer Vision/Intelligent Manufacturing
Natural Language Processing/Smart Medicine
Blockchain, IoT Security, Authentication, Cryptology
Low Earth Orbit Satellite Tracking