Accessibility, transcription, and access everywhere

Abstract

Accessibility in the workplace and in academic settings has increased dramatically for users with disabilities, driven by greater awareness, legislative mandate, and technological improvements. Gaps, however, remain. For persons who are deaf and hard of hearing in particular, full participation requires complete access to audio materials, both for live settings and for prerecorded audio and visual information. Even for users with adequate hearing, captioned or transcribed materials offer another modality for information access, one that can be particularly useful in certain situations, such as listening in noisy environments, interpreting speakers with strong accents, or searching audio media for specific information. Providing this level of access through fully automated means is currently beyond the state of the art. This paper details a number of key advances in audio access that have occurred over the last five years. We describe the Liberated Learning Project, a consortium of universities worldwide, which is piloting technologies to create real-time access for students who are deaf and hard of hearing, without intermediary assistance. In support of this project, IBM Research has created the ViaScribee tool that converts speech recognition output to a viable captioning interface. Additional inventions and incremental improvements to speech recognition for captioning are described, as well as future directions.

Automated generation of ‘good enough’ transcripts as a first step to transcription of audio-recorded data

“…Lewis and Jackson (2001) have demonstrated that script comprehension of deaf and also hearing impaired students was greater with captioned videos. Bain et al (2005) describe key advances in audio access that have occurred since 2000, mentioning the intention to create real-time access for students who are deaf and hard of hearing, without intermediary assistance. They utilise a tool called Viascribe to convert speech recognition output to a viable captioning interface.…”

Designing Mobile Web Solutions for Interaction Scenarios Involving Disabled People

“…Moreover, it can also vibrate Chuty's and her parents' smartphones which is better than turning lights in the room on and off to notify them as this may not be noticeable in sunlight. Captions can be of value to everybody, especially people with no useful hearing, and were selected as the solution of choice [27], [28], [29], [30]. Thai speech recognition is not very accurate for spontaneous speech [31] and therefore as Suchat already knows what he plans to say the best solution is pre-prepared summary captions.As he presents his talk Suchat controls the changing preprepared captions on the mobile website using his smartphone.…”

Simultaneous translation of lectures and speeches

“…The goal of the MIT Spoken Lecture Processing project (Glass et al 2007) is to improve access to on-line audio/visual recordings of academic lectures by developing tools for the processing, transcription, indexing, segmentation, summarization, retrieval and browsing of this medium. In the Liberated Learning Consortium (Bain et al 2005), instead the goal is to provide real-time, highquality automatic speech transcription to aid hearing-impaired students. Research is conducted not only on improving the recognition quality, but also on the delivery aspect.…”