The use of ASR (automatic speech recognition) to convert speech to text is everywhere. It can be a very useful accessibility tool for people with hearing loss, enabling captioning on demand for live, face-to-face conversations, remote meetings, telephone conversations, media, and more.
How do ASR-generated captions, especially with the use of AI-based techniques, compare to human-generated captions? Even more fundamental is how do we measure caption performance? These and other topics are open for discussion in the ASR and Speech-to-Text group.
The Tech Forum Community is a place for positive, inclusive engagement. You can start a discussion, contribute your experiences and perspective, discover and post resources and events, and learn from others. If you like this group, use the social sharing buttons to spread the word.
