{"id":"https://openalex.org/W4392902837","doi":"https://doi.org/10.1109/icassp48485.2024.10446474","title":"Learning Contextualized Representation on Discrete Space Via Hierarchical Product Quantization","display_name":"Learning Contextualized Representation on Discrete Space Via Hierarchical Product Quantization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902837","doi":"https://doi.org/10.1109/icassp48485.2024.10446474"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446474","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5031214691","display_name":"Hyung Yong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Yong Kim","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027173062","display_name":"Yunkyu Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunkyu Lim","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740584","display_name":"Jihwan Park","orcid":"https://orcid.org/0009-0007-2223-7278"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihwan Park","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026087844","display_name":"Jin-Seok Park","orcid":"https://orcid.org/0000-0003-4099-2027"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinseok Park","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059677906","display_name":"Youshin Lim","orcid":"https://orcid.org/0000-0003-3328-0064"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youshin Lim","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114048496","display_name":"Seung Woo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung Woo Yu","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025565566","display_name":"Hanbin Lee","orcid":"https://orcid.org/0000-0002-4545-0027"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanbin Lee","raw_affiliation_strings":["42dot Inc,Seoul,Republic of Korea","42dot Inc, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc, Seoul, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02511376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"12336","last_page":"12340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"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":0.7187678813934326},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6001325249671936},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5368075966835022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4614514112472534},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4446299970149994},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.41398143768310547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3845469057559967},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1754627525806427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1467507779598236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7187678813934326},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6001325249671936},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5368075966835022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4614514112472534},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4446299970149994},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.41398143768310547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3845469057559967},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1754627525806427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1467507779598236},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446474","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2889519245","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2953190524","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4226033575","https://openalex.org/W4296069135","https://openalex.org/W4319862670","https://openalex.org/W4375869040","https://openalex.org/W4375869189","https://openalex.org/W4377865046","https://openalex.org/W4381786045","https://openalex.org/W4394671563","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6795952400","https://openalex.org/W6803547063","https://openalex.org/W6848208918","https://openalex.org/W6852781825"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2979160909","https://openalex.org/W2114837856","https://openalex.org/W2795079307","https://openalex.org/W2961085424","https://openalex.org/W2359364609","https://openalex.org/W2322476848","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W4289681578"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"has":[2],"recently":[3],"demonstrated":[4],"significant":[5],"success":[6],"in":[7,25],"various":[8],"speech":[9,29],"processing":[10],"applications.":[11],"Recent":[12],"studies":[13],"report":[14],"that":[15,62],"pre-training":[16],"with":[17,114],"contextualized":[18,42,99],"continuous":[19,35],"targets":[20,43,77],"plays":[21],"a":[22,57],"crucial":[23],"role":[24],"fine-tuning":[26],"for":[27,85,118],"better":[28],"downstream":[30],"tasks.":[31],"However,":[32],"unlike":[33],"the":[34,64,72,92,95,105,121],"targets,":[36],"it":[37],"is":[38],"challenging":[39],"to":[40,48],"produce":[41],"on":[44],"discrete":[45,100],"space":[46],"due":[47],"unstable":[49],"training.":[50],"To":[51],"address":[52],"this":[53],"issue,":[54],"we":[55],"introduce":[56],"new":[58],"hierarchical":[59],"product":[60],"quantizer":[61,97],"enables":[63],"full":[65],"utilization":[66],"of":[67,75,94],"multi-layer":[68],"features":[69],"by":[70],"reducing":[71],"possible":[73],"case":[74],"quantized":[76],"and":[78,98,110],"preventing":[79],"mode":[80],"collapse":[81],"through":[82],"diversity":[83],"loss":[84],"all":[86],"codebooks.":[87],"Our":[88],"ablation":[89],"study":[90],"confirms":[91],"effectiveness":[93],"proposed":[96,106,122],"targets.":[101],"For":[102],"supervised":[103],"ASR,":[104,120],"model":[107],"outperforms":[108],"wav2vec2":[109],"showed":[111],"comparable":[112],"results":[113],"data2vec.":[115],"In":[116],"addition,":[117],"unsupervised":[119],"method":[123],"surpasses":[124],"two":[125],"baselines.":[126]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}