Abstract: In recent years, the increasing volume of audio-based content in academic and professional environments has necessitated efficient tools for automated note-taking and summarization. The ...

Abstract: Developing successful image captioning systems for blind users is a complex problem in computer vision, in which one extracts meaningful textual descriptions from visual inputs. We aim to ...

Miravoice, a startup using AI voice agents to conduct long-form phone surveys, has raised $6.3 million in a seed funding ...

Nobody wants to look silly yelling at an AI in a meeting. Making voice agents work at the office is more about "human" feel ...