{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/speech-reconstruction-with-reminiscent-sound","title":"Speech Reconstruction with Reminiscent Sound via Visual Voice Memory","arxiv_id":null,"date":"2021-11-17","proceeding":"IEEE/ACM Transactions on Audio, Speech, and Language Processing 2021 11","authors":["Joanna Hong","Minsu Kim","Se Jin Park","Yong Man Ro"],"abstract":"The goal of this work is to reconstruct speech from silent video, in both speaker dependent and independent ways. Unlike previous works that have been mostly restricted to a speaker dependent setting, we propose Visual Voice memory to restore essential auditory information to generate proper speech from different speakers and even unseen speakers. The proposed memory takes additional auditory information that corresponds to the input face movements and stores the auditory contexts that can be recalled by the given input visual features. Specifically, the Visual Voice memory contains value and key memory slots, where value memory slots are for saving the audio features, and key memory slots are for storing the visual features in the same location of the saved audio features. Guiding each memory to properly save each feature, the model can adequately produce the speech. Hence, our method employs both video and audio information during training time but does not require any additional auditory input during inference. Our key contributions are: (1) proposing the Visual Voice memory that brings rich information of audio that complements the visual features, thus producing high-quality speech from silent video, and (2) enabling multi-speaker and unseen speaker training by memorizing auditory features and the corresponding visual features. We validate the proposed framework on GRID and Lip2Wav datasets and show that our method surpasses the performance of previous works on both multi-speaker and speaker independent settings. We also demonstrate that the Visual Voice memory contains meaningful information to reconstruct speech.","url_abs":"https://ieeexplore.ieee.org/document/9618777","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9618777","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-reconstruction-with-reminiscent-sound","repo_url":"https://github.com/joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"speaker-specific-lip-to-speech-synthesis","task_name":"Speaker-Specific Lip to Speech Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on","task":"Speaker-Specific Lip to Speech Synthesis","dataset":"GRID corpus (mixed-speech)","model":"Visual Voice Memory","rank_in_archive_order":1,"of":2,"metrics":{"ESTOI":"0.579","PESQ":"1.984","STOI":"0.738"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-7","task":"Speaker-Specific Lip to Speech Synthesis","dataset":"Lip2Wav (Chem)","model":"Visual Voice Memory","rank_in_archive_order":1,"of":2,"metrics":{"ESTOI":"0.429","PESQ":"1.529","STOI":"0.566"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-6","task":"Speaker-Specific Lip to Speech Synthesis","dataset":"Lip2Wav (Chess)","model":"Visual Voice Memory","rank_in_archive_order":1,"of":2,"metrics":{"ESTOI":"0.334","PESQ":"1.503","STOI":"0.506"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-5","task":"Speaker-Specific Lip to Speech Synthesis","dataset":"Lip2Wav (DL)","model":"Visual Voice Memory","rank_in_archive_order":1,"of":2,"metrics":{"ESTOI":"0.402","PESQ":"1.612","STOI":"0.576"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-3","task":"Speaker-Specific Lip to Speech Synthesis","dataset":"Lip2Wav (EH)","model":"Visual Voice Memory","rank_in_archive_order":1,"of":2,"metrics":{"ESTOI":"0.304","PESQ":"1.362","STOI":"0.463"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-specific-lip-to-speech-synthesis-on-4","task":"Speaker-Specific Lip to Speech Synthesis","dataset":"Lip2Wav (HS)","model":"Visual Voice Memory","rank_in_archive_order":1,"of":2,"metrics":{"ESTOI":"0.337","PESQ":"1.366","STOI":"0.504"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"joannahong/Speech-Reconstruction-with-Reminiscent-Sound-via-Visual-Voice-Memory","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7d7dbd6a8c6126e0a3dcc9cd79d48033bd79aea579847e0697560cd0feb71f65","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}