{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/speech-based-visual-question-answering","title":"Speech-Based Visual Question Answering","arxiv_id":"1705.00464","date":"2017-05-01","proceeding":null,"authors":["Ted Zhang","Dengxin Dai","Tinne Tuytelaars","Marie-Francine Moens","Luc van Gool"],"abstract":"This paper introduces speech-based visual question answering (VQA), the task\nof generating an answer given an image and a spoken question. Two methods are\nstudied: an end-to-end, deep neural network that directly uses audio waveforms\nas input versus a pipelined approach that performs ASR (Automatic Speech\nRecognition) on the question, followed by text-based visual question answering.\nFurthermore, we investigate the robustness of both methods by injecting various\nlevels of noise into the spoken question and find both methods to be tolerate\nnoise at similar levels.","url_abs":"http://arxiv.org/abs/1705.00464v2","url_pdf":"http://arxiv.org/pdf/1705.00464v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"speech-based-visual-question-answering","repo_url":"https://github.com/zted/sbvqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.00464","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}