HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
It addresses a bottleneck in multi-modal AI for video dialogue systems, improving audio utilization for more accurate responses.
The paper tackles the problem of Video-grounded Dialogue (VGD) systems ignoring audio data, leading to 'deaf responses', by proposing the HEAR framework to selectively attend to audio when needed, enhancing accuracy and audibility in a model-agnostic way, validated on AVSD@DSTC7 and AVSD@DSTC8 datasets.
Video-grounded Dialogue (VGD) aims to answer questions regarding a given multi-modal input comprising video, audio, and dialogue history. Although there have been numerous efforts in developing VGD systems to improve the quality of their responses, existing systems are competent only to incorporate the information in the video and text and tend to struggle in extracting the necessary information from the audio when generating appropriate responses to the question. The VGD system seems to be deaf, and thus, we coin this symptom of current systems' ignoring audio data as a deaf response. To overcome the deaf response problem, Hearing Enhanced Audio Response (HEAR) framework is proposed to perform sensible listening by selectively attending to audio whenever the question requires it. The HEAR framework enhances the accuracy and audibility of VGD systems in a model-agnostic manner. HEAR is validated on VGD datasets (i.e., AVSD@DSTC7 and AVSD@DSTC8) and shows effectiveness with various VGD systems.