{"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/combining-residual-networks-with-lstms-for","title":"Combining Residual Networks with LSTMs for Lipreading","arxiv_id":"1703.04105","date":"2017-03-12","proceeding":null,"authors":["Themos Stafylakis","Georgios Tzimiropoulos"],"abstract":"We propose an end-to-end deep learning architecture for word-level visual\nspeech recognition. The system is a combination of spatiotemporal\nconvolutional, residual and bidirectional Long Short-Term Memory networks. We\ntrain and evaluate it on the Lipreading In-The-Wild benchmark, a challenging\ndatabase of 500-size target-words consisting of 1.28sec video excerpts from BBC\nTV broadcasts. The proposed network attains word accuracy equal to 83.0,\nyielding 6.8 absolute improvement over the current state-of-the-art, without\nusing information about word boundaries during training or testing.","url_abs":"http://arxiv.org/abs/1703.04105v4","url_pdf":"http://arxiv.org/pdf/1703.04105v4.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":"combining-residual-networks-with-lstms-for","repo_url":"https://github.com/tstafylakis/Lipreading-ResNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"combining-residual-networks-with-lstms-for","repo_url":"https://github.com/gaalszandi/visual_speech_recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"combining-residual-networks-with-lstms-for","repo_url":"https://github.com/manideep2510/Lipreading-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"combining-residual-networks-with-lstms-for","repo_url":"https://github.com/michaeltrs/Lipreading_ResNet_LSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"lip-reading","task_name":"Lip Reading"},{"task_slug":"lipreading","task_name":"Lipreading"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lipreading-on-lip-reading-in-the-wild","task":"Lipreading","dataset":"Lip Reading in the Wild","model":"3D Conv + ResNet-34 + Bi-LSTM","rank_in_archive_order":22,"of":22,"metrics":{"Top-1 Accuracy":"83.00"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04105"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michaeltrs/Lipreading_ResNet_LSTM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manideep2510/Lipreading-Keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaalszandi/visual_speech_recognition","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tstafylakis/Lipreading-ResNet","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"f51e93851c97c085","entry":"labels_to_text","repo":"manideep2510/Lipreading-Keras","repo_kind":"listed","path":"predict_lip.py","file_url":"https://github.com/manideep2510/Lipreading-Keras/blob/HEAD/predict_lip.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f51e93851c97c085"}},{"code_sha256_prefix":"d39d1cd46009e948","entry":"numericalSort","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d39d1cd46009e948"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}