SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition
This work addresses a domain-specific challenge in AVSR for transcribing technical speech in academic presentations, though it is incremental as it builds on existing AVSR methods with a new dataset.
The paper tackles the problem of audio-visual speech recognition (AVSR) in scientific paper explanation videos by constructing the SlideAVSR dataset, which includes speech and slide text, and proposes DocWhisper as a baseline model that effectively transcribes technical terminologies by referencing slide texts.
Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio. In AVSR, considerable efforts have been directed at datasets for facial features such as lip-readings, while they often fall short in evaluating the image comprehension capabilities in broader contexts. In this paper, we construct SlideAVSR, an AVSR dataset using scientific paper explanation videos. SlideAVSR provides a new benchmark where models transcribe speech utterances with texts on the slides on the presentation recordings. As technical terminologies that are frequent in paper explanations are notoriously challenging to transcribe without reference texts, our SlideAVSR dataset spotlights a new aspect of AVSR problems. As a simple yet effective baseline, we propose DocWhisper, an AVSR model that can refer to textual information from slides, and confirm its effectiveness on SlideAVSR.