{"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/syllable-discovery-and-cross-lingual","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","arxiv_id":"2305.11435","date":"2023-05-19","proceeding":null,"authors":["Puyuan Peng","Shang-Wen Li","Okko Räsänen","Abdelrahman Mohamed","David Harwath"],"abstract":"In this paper, we show that representations capturing syllabic units emerge when training a self-supervised speech model with a visually-grounded training objective. We demonstrate that a nearly identical model architecture (HuBERT) trained with a masked language modeling loss does not exhibit this same ability, suggesting that the visual grounding objective is responsible for the emergence of this phenomenon. We propose the use of a minimum cut algorithm to automatically predict syllable boundaries in speech, followed by a 2-stage clustering method to group identical syllables together. We show that our model not only outperforms a state-of-the-art syllabic segmentation method on the language it was trained on (English), but also generalizes in a zero-shot fashion to Estonian. Finally, we show that the same model is capable of zero-shot generalization for a word segmentation task on 4 other languages from the Zerospeech Challenge, in some cases beating the previous state-of-the-art.","url_abs":"https://arxiv.org/abs/2305.11435v2","url_pdf":"https://arxiv.org/pdf/2305.11435v2.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":"syllable-discovery-and-cross-lingual","repo_url":"https://github.com/jasonppy/syllable-discovery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"syllable-discovery-and-cross-lingual","repo_url":"https://github.com/cheoljun95/sdhubert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11435"}},"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/jasonppy/syllable-discovery","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cheoljun95/sdhubert","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":2,"ran_honours":2,"ran_fixture":1,"unverified":10},"by_repo_kind":{"official":{"samples":16,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"4d25be8ebf17fde1","entry":"bool_flag","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/vit_utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vit_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4d25be8ebf17fde1"}},{"code_sha256_prefix":"2b5489053b222e00","entry":"clip_gradients","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/vit_utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vit_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5489053b222e00"}},{"code_sha256_prefix":"361a6b24f11fc50a","entry":"cosine_scheduler","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/vit_utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vit_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"361a6b24f11fc50a"}},{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"code_sha256_prefix":"c2f0705ed8e6f7e6","entry":"gelu","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"code_sha256_prefix":"05ead5734e7a624a","entry":"Margin_InfoNCE_loss","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"05ead5734e7a624a"}},{"code_sha256_prefix":"e6255f746846c117","entry":"cal_code_boundary","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"prepare_zs20_submit_vadcon.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/prepare_zs20_submit_vadcon.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e6255f746846c117"}},{"code_sha256_prefix":"7d5acd7d52b1da2f","entry":"cls_attn_seg_feats","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"estonian.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/estonian.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7d5acd7d52b1da2f"}},{"code_sha256_prefix":"207b963d4d0d89c3","entry":"cls_attn_seg_feats","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"save_seg_feats_zs20_vadcon.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/save_seg_feats_zs20_vadcon.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"207b963d4d0d89c3"}},{"code_sha256_prefix":"6b7104858152a9ea","entry":"compute_f1","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"estonian.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/estonian.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6b7104858152a9ea"}},{"code_sha256_prefix":"cb8fc284951267b6","entry":"get_word_ali","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"save_seg_feats_mincut.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/save_seg_feats_mincut.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cb8fc284951267b6"}},{"code_sha256_prefix":"25ab494dfd483b73","entry":"get_word_ali","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"unit_analysis_boundary_only.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/unit_analysis_boundary_only.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"25ab494dfd483b73"}},{"code_sha256_prefix":"35070d2f37830ca3","entry":"parse_faiss_specs","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"kmeans_zs20_vadcon.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/kmeans_zs20_vadcon.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"35070d2f37830ca3"}},{"code_sha256_prefix":"3aae9623741abc40","entry":"vit_small","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3aae9623741abc40"}},{"code_sha256_prefix":"7d962f3bf8a0e816","entry":"vit_tiny","repo":"jasonppy/syllable-discovery","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7d962f3bf8a0e816"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}