{"id":"https://openalex.org/W3161411634","doi":"https://doi.org/10.1109/icassp39728.2021.9413680","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","display_name":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161411634","doi":"https://doi.org/10.1109/icassp39728.2021.9413680","mag":"3161411634"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063609244","display_name":"Henry Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Henry Zhou","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3050","last_page":"3054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.7588071227073669},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6993045210838318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.672241747379303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365253686904907},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5064162015914917},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4946574866771698},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4890309274196625},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4838906228542328},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.4772355854511261},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44890210032463074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41551274061203003},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16644400358200073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588071227073669},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6993045210838318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.672241747379303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365253686904907},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5064162015914917},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4946574866771698},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4890309274196625},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4838906228542328},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.4772355854511261},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44890210032463074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41551274061203003},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16644400358200073},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2118154032","https://openalex.org/W2124509324","https://openalex.org/W2519091744","https://openalex.org/W2547875792","https://openalex.org/W2752796333","https://openalex.org/W2789543585","https://openalex.org/W2811079561","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2930682606","https://openalex.org/W2933138175","https://openalex.org/W2950365520","https://openalex.org/W2953190524","https://openalex.org/W2962942158","https://openalex.org/W2963263347","https://openalex.org/W2963341956","https://openalex.org/W2963799213","https://openalex.org/W2970119519","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2995680346","https://openalex.org/W2996383576","https://openalex.org/W3015419784","https://openalex.org/W3036601975","https://openalex.org/W3095361818","https://openalex.org/W3099782249","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W3127686677","https://openalex.org/W4297808394","https://openalex.org/W6729448088","https://openalex.org/W6734376636","https://openalex.org/W6748381668","https://openalex.org/W6753018729","https://openalex.org/W6755207826","https://openalex.org/W6761553608","https://openalex.org/W6769196770","https://openalex.org/W6769313972","https://openalex.org/W6770596778","https://openalex.org/W6780218876","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2461917396","https://openalex.org/W1966667550","https://openalex.org/W2037497866","https://openalex.org/W1502435251","https://openalex.org/W62001224","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150","https://openalex.org/W3145681568","https://openalex.org/W2079308190"],"abstract_inverted_index":{"Neural":[0],"latent":[1],"variable":[2],"models":[3],"enable":[4],"the":[5,33,39,77],"discovery":[6,51],"of":[7,19,48,74],"interesting":[8],"structure":[9],"in":[10,46],"speech":[11],"audio":[12],"data.":[13],"This":[14],"paper":[15],"presents":[16],"a":[17],"comparison":[18],"two":[20],"different":[21],"approaches":[22],"which":[23],"are":[24],"broadly":[25],"based":[26],"on":[27,76],"predicting":[28],"future":[29,59],"time-steps":[30],"or":[31],"auto-encoding":[32],"input":[34],"signal.":[35],"Our":[36],"study":[37],"compares":[38],"representations":[40],"learned":[41],"by":[42],"vq-vae":[43],"and":[44,52],"vq-wav2vec":[45,63],"terms":[47],"sub-word":[49],"unit":[50],"phoneme":[53,81],"recognition":[54],"performance.":[55,66],"Results":[56],"show":[57],"that":[58],"time-step":[60],"prediction":[61],"with":[62],"achieves":[64,70],"better":[65],"The":[67],"best":[68],"system":[69],"an":[71],"error":[72],"rate":[73],"13.22":[75],"ZeroSpeech":[78],"2019":[79],"ABX":[80],"discrimination":[82],"challenge.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}