{"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/wav2sem-plug-and-play-audio-semantic","title":"Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation","arxiv_id":"2505.23290","date":"2025-05-29","proceeding":"CVPR 2025 1","authors":["Hao Li","Ju Dai","Xin Zhao","Feng Zhou","Junjun Pan","Lei LI"],"abstract":"In 3D speech-driven facial animation generation, existing methods commonly employ pre-trained self-supervised audio models as encoders. However, due to the prevalence of phonetically similar syllables with distinct lip shapes in language, these near-homophone syllables tend to exhibit significant coupling in self-supervised audio feature spaces, leading to the averaging effect in subsequent lip motion generation. To address this issue, this paper proposes a plug-and-play semantic decorrelation module-Wav2Sem. This module extracts semantic features corresponding to the entire audio sequence, leveraging the added semantic information to decorrelate audio encodings within the feature space, thereby achieving more expressive audio features. Extensive experiments across multiple Speech-driven models indicate that the Wav2Sem module effectively decouples audio features, significantly alleviating the averaging effect of phonetically similar syllables in lip shape generation, thereby enhancing the precision and naturalness of facial animations. Our source code is available at https://github.com/wslh852/Wav2Sem.git.","url_abs":"https://arxiv.org/abs/2505.23290v1","url_pdf":"https://arxiv.org/pdf/2505.23290v1.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":"wav2sem-plug-and-play-audio-semantic","repo_url":"https://github.com/wslh852/wav2sem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"motion-generation","task_name":"Motion Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.23290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23290"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/wslh852/Wav2Sem","reach":null}],"summary":{"ran":9,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":12,"samples":[{"code_sha256_prefix":"531468718cc2e08d","entry":"Wav2Vec2Attention","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"531468718cc2e08d"}},{"code_sha256_prefix":"79fb58557dde3a6d","entry":"Wav2Vec2FeatureExtractor","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"79fb58557dde3a6d"}},{"code_sha256_prefix":"8fd95ea4c7fdb7f4","entry":"Wav2Vec2FeatureProjection","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fd95ea4c7fdb7f4"}},{"code_sha256_prefix":"2d5e760c8a4bec53","entry":"Wav2Vec2FeedForward","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d5e760c8a4bec53"}},{"code_sha256_prefix":"533d5bcb92d814d2","entry":"Wav2Vec2GroupNormConvLayer","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"533d5bcb92d814d2"}},{"code_sha256_prefix":"f31cb923afe6e950","entry":"Wav2Vec2LayerNormConvLayer","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f31cb923afe6e950"}},{"code_sha256_prefix":"2967594d3760963b","entry":"Wav2Vec2NoLayerNormConvLayer","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2967594d3760963b"}},{"code_sha256_prefix":"96d4171b1f802419","entry":"Wav2Vec2PositionalConvEmbedding","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"96d4171b1f802419"}},{"code_sha256_prefix":"359cf7d745b84cb5","entry":"Wav2Vec2SamePadLayer","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"359cf7d745b84cb5"}},{"code_sha256_prefix":"185c6c4d52d82758","entry":"Wav2Bert","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"185c6c4d52d82758"}},{"code_sha256_prefix":"cb1ee4513c58d21f","entry":"Wav2Vec2Encoder","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb1ee4513c58d21f"}},{"code_sha256_prefix":"108af0871b1f7d65","entry":"Wav2Vec2EncoderLayer","repo":"wslh852/Wav2Sem","repo_kind":"official","path":"CodeTalker_Wav2Sem/models/wav2sem.py","file_url":"https://github.com/wslh852/Wav2Sem/blob/HEAD/CodeTalker_Wav2Sem/models/wav2sem.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"108af0871b1f7d65"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}