AAAI Publications, Twenty-Sixth AAAI Conference on Artificial Intelligence

Font Size: 
Online Sequence Alignment for Real-Time Audio Transcription by Non-Experts
Walter S. Lasecki, Christopher D. Miller, Donato Borrello, Jeffrey P. Bigham

Last modified: 2012-07-14


Real-time transcription provides deaf and hard of hearing people visual access to spoken content, such as classroom instruction, and other live events. Currently, the only reliable source of real-time transcriptions are expensive, highly-trained experts who are able to keep up with speaking rates. Automatic speech recognition is cheaper but produces too many errors in realistic settings. We introduce a new approach in which partial captions from multiple non-experts are combined to produce a high-quality transcription in real-time. We demonstrate the potential of this approach with data collected from 20 non-expert captionists.


real-time captioning; real-time transcription; real-time crowdsourcing; assistive technology

Full Text: PDF