{"id":"https://openalex.org/W4390887450","doi":"https://doi.org/10.1109/taslp.2024.3350888","title":"Slowness Regularized Contrastive Predictive Coding for Acoustic Unit Discovery","display_name":"Slowness Regularized Contrastive Predictive Coding for Acoustic Unit Discovery","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390887450","doi":"https://doi.org/10.1109/taslp.2024.3350888"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3350888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3350888","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabhchand Bhati","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":"https://orcid.org/0000-0001-6477-3895","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing, Johns Hopkins University, USA","Human Language Technology Center of Excellence, Johns Hopkins University, USA"],"raw_orcid":"https://orcid.org/0000-0001-9459-8426","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["Meaning.Team Inc., Johns Hopkins University, Baltimore, MD, USA","Meaning.Team Inc, USA"],"raw_orcid":"https://orcid.org/0000-0002-8245-0413","affiliations":[{"raw_affiliation_string":"Meaning.Team Inc., Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Meaning.Team Inc, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Velazquez","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":"https://orcid.org/0000-0002-3033-7005","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence, Johns Hopkins University, USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":"https://orcid.org/0000-0002-4489-5753","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4846,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68290906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"4277","last_page":"4287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.7101340293884277},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6695133447647095},{"id":"https://openalex.org/keywords/slowness","display_name":"Slowness","score":0.5585569739341736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.545778214931488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49437737464904785},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4623725414276123},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4587540626525879},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4463193714618683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1815963089466095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101340293884277},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6695133447647095},{"id":"https://openalex.org/C11940443","wikidata":"https://www.wikidata.org/wiki/Q16965645","display_name":"Slowness","level":2,"score":0.5585569739341736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.545778214931488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49437737464904785},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4623725414276123},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4587540626525879},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4463193714618683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1815963089466095},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3350888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3350888","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1796128977","https://openalex.org/W2020607164","https://openalex.org/W2057007397","https://openalex.org/W2078769636","https://openalex.org/W2117041980","https://openalex.org/W2146444479","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2170659185","https://openalex.org/W2346964103","https://openalex.org/W2395899413","https://openalex.org/W2468716020","https://openalex.org/W2747192917","https://openalex.org/W2752796333","https://openalex.org/W2786608204","https://openalex.org/W2787447541","https://openalex.org/W2890718354","https://openalex.org/W2936774411","https://openalex.org/W2940544976","https://openalex.org/W2963620343","https://openalex.org/W2963720603","https://openalex.org/W2964169922","https://openalex.org/W2973049979","https://openalex.org/W3016181583","https://openalex.org/W3095361818","https://openalex.org/W3096656254","https://openalex.org/W3097159218","https://openalex.org/W3100270690","https://openalex.org/W3144810982","https://openalex.org/W3159481202","https://openalex.org/W3197974236","https://openalex.org/W3198134274","https://openalex.org/W3198782837","https://openalex.org/W3198815374","https://openalex.org/W3204915839","https://openalex.org/W3209993061","https://openalex.org/W4301204483","https://openalex.org/W4313182775","https://openalex.org/W4385245566","https://openalex.org/W4385822676","https://openalex.org/W6640963894","https://openalex.org/W6675022971","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6774456908","https://openalex.org/W6780218876","https://openalex.org/W6799172387","https://openalex.org/W6838949706","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3103461978","https://openalex.org/W2356299150","https://openalex.org/W2144966994","https://openalex.org/W2003964906","https://openalex.org/W4389273484","https://openalex.org/W4378230892","https://openalex.org/W3017010751","https://openalex.org/W2180486137","https://openalex.org/W1984459742","https://openalex.org/W2564629062"],"abstract_inverted_index":{"Self-supervised":[0],"methods":[1],"such":[2,31],"as":[3,32],"Contrastive":[4],"predictive":[5],"Coding":[6],"(CPC)":[7],"have":[8],"greatly":[9],"improved":[10],"the":[11,14,21,50,53,61,76,91,119,122,148,162,173,178],"quality":[12],"of":[13,23,115,121,129,161,164],"unsupervised":[15],"representations.":[16],"These":[17],"representations":[18,38],"significantly":[19],"reduce":[20],"amount":[22,163],"labeled":[24],"data":[25,117,142,158,165],"needed":[26],"for":[27,167],"downstream":[28],"task":[29],"performance,":[30],"automatic":[33,105],"speech":[34,106],"recognition.":[35,107],"CPC":[36,110,124,175],"learns":[37],"by":[39],"learning":[40],"to":[41,141],"predict":[42],"future":[43],"frames":[44],"given":[45],"current":[46],"frames.":[47],"Based":[48],"on":[49,75,94,112,126,177],"observation":[51],"that":[52,71,135],"acoustic":[54,101],"information,":[55],"e.g.,":[56],"phones,":[57],"changes":[58],"slower":[59],"than":[60],"feature":[62],"extraction":[63],"rate":[64],"in":[65],"CPC,":[66],"we":[67,79],"propose":[68,80],"regularization":[69,82,137],"techniques":[70,138],"impose":[72],"slowness":[73],"constraints":[74],"features.":[77],"Here":[78],"two":[81],"techniques:":[83],"Self-expressing":[84],"constraint":[85],"and":[86,96,104,144],"Left-or-Right":[87],"regularization.":[88],"We":[89,132],"evaluate":[90],"proposed":[92],"model":[93],"ABX":[95,179],"linear":[97],"phone":[98],"classification":[99],"tasks,":[100],"unit":[102],"discovery,":[103],"The":[108],"regularized":[109,170],"trained":[111,125],"100":[113],"hours":[114,128],"unlabeled":[116,130],"matches":[118],"performance":[120],"baseline":[123,174],"360":[127],"data.":[131],"also":[133],"show":[134],"our":[136,169],"are":[139],"complementary":[140],"augmentation":[143],"can":[145],"further":[146],"boost":[147],"system's":[149],"performance.":[150],"In":[151],"monolingual,":[152],"cross-lingual,":[153],"or":[154],"multilingual":[155],"settings,":[156],"with/without":[157],"augmentation,":[159],"regardless":[160],"used":[166],"training,":[168],"models":[171,176],"outperformed":[172],"task.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}