{"id":"https://openalex.org/W4402115980","doi":"https://doi.org/10.21437/interspeech.2024-787","title":"SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech","display_name":"SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402115980","doi":"https://doi.org/10.21437/interspeech.2024-787"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-787","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-787","pdf_url":"https://www.isca-archive.org/interspeech_2024/lin24g_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/lin24g_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004441972","display_name":"Jingru Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jingru Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077069016","display_name":"Junyi Ao","orcid":"https://orcid.org/0000-0001-8979-0835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyi Ao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004441972"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.669,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74890834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"597","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9800999760627747,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9232000112533569,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7744942903518677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6823285818099976},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6774060726165771},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5251806974411011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4097209870815277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744942903518677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6823285818099976},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6774060726165771},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5251806974411011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097209870815277},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-787","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-787","pdf_url":"https://www.isca-archive.org/interspeech_2024/lin24g_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-787","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-787","pdf_url":"https://www.isca-archive.org/interspeech_2024/lin24g_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4714111969","display_name":null,"funder_award_id":"AISG2-TC-","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G6795395860","display_name":null,"funder_award_id":"AISG2-TC-2022-004","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402115980.pdf","grobid_xml":"https://content.openalex.org/works/W4402115980.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"It":[0],"was":[1],"shown":[2],"that":[3,108],"pre-trained":[4,46,117],"models":[5,20],"with":[6,84],"self-supervised":[7],"learning":[8],"(SSL)":[9],"techniques":[10],"are":[11,21,67],"effective":[12],"in":[13,30,56,63],"various":[14],"downstream":[15],"speech":[16,25],"tasks.However,":[17],"most":[18],"such":[19],"trained":[22],"on":[23,38],"singlespeaker":[24],"data,":[26],"limiting":[27],"their":[28],"effectiveness":[29],"mixture":[31,39,49,66],"speech.This":[32,40],"motivates":[33],"us":[34],"to":[35,99],"explore":[36],"pre-training":[37],"work":[41],"presents":[42],"SA-WavLM,":[43],"a":[44,93],"novel":[45],"model":[47],"for":[48],"speech.Specifically,":[50],"SA-WavLM":[51,80,109],"follows":[52],"an":[53],"\"extract-merge-predict\"":[54],"pipeline":[55],"which":[57],"the":[58,64,75,85,88,101,104,115],"representations":[59],"of":[60,87],"each":[61],"speaker":[62,94,105],"input":[65],"first":[68],"extracted":[69],"individually":[70],"and":[71],"then":[72],"merged":[73],"before":[74],"final":[76],"prediction.In":[77],"this":[78],"pipeline,":[79],"performs":[81],"speaker-informed":[82],"extractions":[83],"consideration":[86],"interactions":[89],"between":[90],"different":[91],"speakers.Furthermore,":[92],"shuffling":[95],"strategy":[96],"is":[97],"proposed":[98],"enhance":[100],"robustness":[102],"towards":[103],"absence.Experiments":[106],"show":[107],"either":[110],"matches":[111],"or":[112],"improves":[113],"upon":[114],"state-of-the-art":[116],"models.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}