{"id":"https://openalex.org/W3094781961","doi":"https://doi.org/10.21437/interspeech.2020","title":"Interspeech 2020","display_name":"Interspeech 2020","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3094781961","doi":"https://doi.org/10.21437/interspeech.2020","mag":"3094781961"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"proceedings"},"type":"paratext","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.15288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073465014","display_name":"Masood Mortazavi","orcid":"https://orcid.org/0009-0000-1825-244X"},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mortazavi, Masood S.","raw_affiliation_strings":["Futurewei Technologies, Santa Clara, California, USA"],"affiliations":[{"raw_affiliation_string":"Futurewei Technologies, Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210146936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073465014"],"corresponding_institution_ids":["https://openalex.org/I4210146936"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.994700014591217,"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":0.994700014591217,"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":0.9746999740600586,"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/T10028","display_name":"Topic Modeling","score":0.9689000248908997,"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":0.824428379535675},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6999174356460571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849930047988892},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5822493433952332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5761314630508423},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5632479786872864},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5193451642990112},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5178804397583008},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4811212122440338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4733966588973999},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46985068917274475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4369427561759949},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4219430088996887},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4218846559524536},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08387553691864014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824428379535675},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6999174356460571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849930047988892},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5822493433952332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5761314630508423},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5632479786872864},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5193451642990112},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5178804397583008},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4811212122440338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4733966588973999},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46985068917274475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4369427561759949},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4219430088996887},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4218846559524536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08387553691864014},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"proceedings"},{"id":"pmh:oai:riunet.upv.es:10251/213952","is_oa":false,"landing_page_url":"http://hdl.handle.net/10251/213952","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2010.15288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15288","pdf_url":"https://arxiv.org/pdf/2010.15288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.15288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15288","pdf_url":"https://arxiv.org/pdf/2010.15288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094781961.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2016076298","https://openalex.org/W2134670479","https://openalex.org/W2137010615","https://openalex.org/W2194775991","https://openalex.org/W2405756170","https://openalex.org/W2483390977","https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2730658205","https://openalex.org/W2766164908","https://openalex.org/W2950133079","https://openalex.org/W2962753610","https://openalex.org/W2963446712","https://openalex.org/W2963902314","https://openalex.org/W2963966654","https://openalex.org/W2964001192","https://openalex.org/W2964054038","https://openalex.org/W2964115348","https://openalex.org/W2971709506","https://openalex.org/W2972345028","https://openalex.org/W2988907666","https://openalex.org/W2995680346","https://openalex.org/W4232426322","https://openalex.org/W4288595436","https://openalex.org/W4295312788","https://openalex.org/W4394453761"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W4386121542"],"abstract_inverted_index":{"Semantically-aligned":[0],"$(speech,":[1],"image)$":[2],"datasets":[3],"can":[4,96,146],"be":[5,147],"used":[6,41],"to":[7,42,47,64,136],"explore":[8,137],"\"visually-grounded":[9],"speech\".":[10],"In":[11,35],"a":[12],"majority":[13],"of":[14,18,68,127,130,142,153],"existing":[15],"investigations,":[16],"features":[17,45],"an":[19],"image":[20,89],"signal":[21],"are":[22,40,123],"extracted":[23],"using":[24,92],"neural":[25,81],"networks":[26,39],"\"pre-trained\"":[27],"on":[28,33,104],"other":[29,138],"tasks":[30,125],"(e.g.,":[31],"classification":[32],"ImageNet).":[34],"still":[36],"others,":[37],"pre-trained":[38,54,57,106],"extract":[43],"audio":[44,144],"prior":[46],"semantic":[48,112],"embedding.":[49],"Without":[50],"\"transfer":[51],"learning\"":[52],"through":[53],"initialization":[55,107],"or":[56,108],"feature":[58,109],"extraction,":[59],"previous":[60],"results":[61],"have":[62],"tended":[63],"show":[65],"low":[66],"rates":[67,100,155],"recall":[69,99,154],"in":[70,85,156],"$speech":[71,115,157],"\\rightarrow":[72,76,116,120,158,162],"image$":[73,117,159],"and":[74,88,91,114,118,133,160],"$image":[75,119,161],"speech$":[77,121,163],"queries.":[78,164],"Choosing":[79],"appropriate":[80],"architectures":[82],"for":[83],"encoders":[84],"the":[86,140,143],"speech":[87],"branches":[90],"large":[93],"datasets,":[94],"one":[95,135],"obtain":[97],"competitive":[98],"without":[101],"any":[102,105],"reliance":[103],"extraction:":[110],"$(speech,image)$":[111],"alignment":[113],"retrieval":[122],"canonical":[124],"worthy":[126],"independent":[128],"investigation":[129],"their":[131],"own":[132],"allow":[134],"questions---e.g.,":[139],"size":[141],"embedder":[145],"reduced":[148],"significantly":[149],"with":[150],"little":[151],"loss":[152]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-11-09T00:00:00"}