{"id":"https://openalex.org/W3016175755","doi":"https://doi.org/10.1109/icassp40776.2020.9054595","title":"Mixture Factorized Auto-Encoder for Unsupervised Hierarchical Deep Factorization of Speech Signal","display_name":"Mixture Factorized Auto-Encoder for Unsupervised Hierarchical Deep Factorization of Speech Signal","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016175755","doi":"https://doi.org/10.1109/icassp40776.2020.9054595","mag":"3016175755"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5075223216","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0000-0002-9870-4422"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Peng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075223216"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75075127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2019","issue":null,"first_page":"6774","last_page":"6778"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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":0.9948999881744385,"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":0.807346761226654},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8059577941894531},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6355472207069397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.616641640663147},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6031696796417236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5570493936538696},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5436701774597168},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5308526754379272},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5023317337036133},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4948076605796814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45396292209625244},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43838950991630554},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4221414625644684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3751472234725952},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23516622185707092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807346761226654},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8059577941894531},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6355472207069397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616641640663147},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6031696796417236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570493936538696},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5436701774597168},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5308526754379272},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5023317337036133},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4948076605796814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45396292209625244},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43838950991630554},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4221414625644684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3751472234725952},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23516622185707092},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W577640895","https://openalex.org/W1959608418","https://openalex.org/W2087618018","https://openalex.org/W2150769028","https://openalex.org/W2175575774","https://openalex.org/W2296701362","https://openalex.org/W2547875792","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2758785877","https://openalex.org/W2807627734","https://openalex.org/W2808631503","https://openalex.org/W2808697642","https://openalex.org/W2890964092","https://openalex.org/W2952161038","https://openalex.org/W2963618559","https://openalex.org/W2963620343","https://openalex.org/W2963891243","https://openalex.org/W2964058423","https://openalex.org/W2964247977","https://openalex.org/W2966574105","https://openalex.org/W2972705840","https://openalex.org/W2972956697","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4297824908","https://openalex.org/W4391602018","https://openalex.org/W6640963894","https://openalex.org/W6697501834","https://openalex.org/W6729448088","https://openalex.org/W6745117592","https://openalex.org/W6751254666","https://openalex.org/W6764882207","https://openalex.org/W6766364717"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4294770367"],"abstract_inverted_index":{"Speech":[0],"signal":[1,27],"is":[2,46,137,161,186],"constituted":[3],"and":[4,14,54,85,144,192],"contributed":[5],"by":[6,107],"various":[7],"informative":[8],"factors,":[9],"such":[10],"as":[11],"linguistic":[12,43,52,93,190],"content":[13,94,191],"speaker":[15,60,140],"characteristic.":[16],"There":[17],"have":[18],"been":[19],"notable":[20],"recent":[21],"studies":[22,37],"attempting":[23],"to":[24,127,170,188],"factorize":[25],"speech":[26,97,129],"into":[28],"these":[29],"individual":[30],"factors":[31],"without":[32],"requiring":[33],"any":[34],"annotation.":[35],"These":[36],"typically":[38],"assume":[39],"continuous":[40],"representation":[41],"for":[42,72],"content,":[44],"which":[45],"not":[47],"in":[48],"accordance":[49],"with":[50,98,167],"general":[51],"knowledge":[53],"may":[55],"make":[56],"the":[57,67,132,158,183,193],"extraction":[58],"of":[59,79,95,163],"information":[61],"less":[62],"successful.":[63],"This":[64],"paper":[65],"proposes":[66],"mixture":[68,113],"factorized":[69],"auto-encoder":[70],"(mFAE)":[71],"unsupervised":[73,145],"deep":[74],"factorization.":[75],"The":[76,89,115,135,150,174],"encoder":[77],"part":[78],"mFAE":[80,136],"comprises":[81],"a":[82,99,111,171],"frame":[83,90,105,110,124,184],"tokenizer":[84,91,185],"an":[86,119],"utterance":[87,116,159,194],"embedder.":[88],"models":[92],"input":[96],"discrete":[100],"categorical":[101],"distribution.":[102],"It":[103],"performs":[104],"clustering":[106],"assigning":[108],"each":[109],"soft":[112],"label.":[114],"embedder":[117,160,195],"generates":[118],"utterance-level":[120],"vector":[121],"representation.":[122],"A":[123],"decoder":[125],"serves":[126],"reconstruct":[128],"features":[130],"from":[131],"encoders'":[133],"outputs.":[134],"evaluated":[138],"on":[139,153,177],"verification":[141],"(SV)":[142],"task":[143],"subword":[146],"modeling":[147],"(USM)":[148],"task.":[149],"SV":[151],"experiments":[152,176],"VoxCeleb":[154],"1":[155],"show":[156],"that":[157,182],"capable":[162],"extracting":[164],"speaker-discriminative":[165],"embeddings":[166],"performance":[168],"comparable":[169],"x-vector":[172],"baseline.":[173],"USM":[175],"ZeroSpeech":[178],"2017":[179],"dataset":[180],"verify":[181],"able":[187],"capture":[189],"can":[196],"acquire":[197],"speaker-related":[198],"information.":[199]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}