{"id":"https://openalex.org/W4385823277","doi":"https://doi.org/10.21437/interspeech.2023-2044","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","display_name":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823277","doi":"https://doi.org/10.21437/interspeech.2023-2044"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2044","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075735963","display_name":"Puyuan Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puyuan Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016518233","display_name":"Okko R\u00e4s\u00e4nen","orcid":"https://orcid.org/0000-0002-0537-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Okko R\u00e4s\u00e4nen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101170706","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7359373569488525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6445738673210144},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6382446885108948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6356543302536011},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4765801429748535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44275978207588196},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14758050441741943}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7359373569488525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445738673210144},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6382446885108948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6356543302536011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4765801429748535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44275978207588196},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14758050441741943},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-2044","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/207297","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/207297","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2885094885","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2132658536","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2094188777"],"abstract_inverted_index":{"In":[0],"this":[1,41,56],"paper,":[2],"we":[3,116],"show":[4,86,117],"that":[5,24,45,87,118],"representations":[6],"capturing":[7],"syllabic":[8,95],"units":[9],"emerge":[10],"when":[11],"training":[12,20],"a":[13,18,25,33,63,76,93,110,128],"self-supervised":[14],"speech":[15],"model":[16,28,89,121],"with":[17,32],"visually-grounded":[19],"objective.":[21],"We":[22,58,85],"demonstrate":[23],"nearly":[26],"identical":[27,82],"architecture":[29],"(HuBERT)":[30],"trained":[31,103],"masked":[34],"language":[35,100],"modeling":[36],"loss":[37],"does":[38],"not":[39,90],"exhibit":[40],"same":[42,120],"ability,":[43],"suggesting":[44],"the":[46,53,60,99,119,137,144],"visual":[47],"grounding":[48],"objective":[49],"is":[50,122],"responsible":[51],"for":[52,127],"emergence":[54],"of":[55,62,124],"phenomenon.":[57],"propose":[59],"use":[61],"minimum":[64],"cut":[65],"algorithm":[66],"to":[67,80,113],"automatically":[68],"predict":[69],"syllable":[70],"boundaries":[71],"in":[72,109,140],"speech,":[73],"followed":[74],"by":[75],"2-stage":[77],"clustering":[78],"method":[79,97],"group":[81],"syllables":[83],"together.":[84],"our":[88],"only":[91],"outperforms":[92],"state-of-the-art":[94],"segmentation":[96,130],"on":[98,104,132],"it":[101],"was":[102],"(English),":[105],"but":[106],"also":[107],"generalizes":[108],"zero-shot":[111,125],"fashion":[112],"Estonian.":[114],"Finally,":[115],"capable":[123],"generalization":[126],"word":[129],"task":[131],"4":[133],"other":[134],"languages":[135],"from":[136],"Zerospeech":[138],"Challenge,":[139],"some":[141],"cases":[142],"beating":[143],"previous":[145],"state-of-the-art.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
