It's hard to believe that it has been a dozen years since Google introduced machine-generated automatic captions to YouTube. Today, 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 for live, face-to-face conversation, remote meetings, telephone conversations, and more.
How ASR-generated captions compare to human-generated captions is an important question and hot topic. An even more fundamental question has to do with how we measure caption performance. These and other topics are all open for discussion here in the ASR and Speech-to-Text group.
We invite you to share your experiences using ASR-generated captions and learn from the experiences of others. We hope you will be an active group member, engage positively with other members and contribute to advancing our discussions and understanding of the topics. If you like this group, please suggest it to others.
