{"id":"https://openalex.org/W2901265786","doi":"https://doi.org/10.1109/icassp.2019.8683367","title":"Investigating the Effects of Word Substitution Errors on Sentence Embeddings","display_name":"Investigating the Effects of Word Substitution Errors on Sentence Embeddings","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2901265786","doi":"https://doi.org/10.1109/icassp.2019.8683367","mag":"2901265786","pmid":"https://pubmed.ncbi.nlm.nih.gov/33376454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.07021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015429874","display_name":"Rohit Voleti","orcid":"https://orcid.org/0000-0002-5943-3471"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohit Voleti","raw_affiliation_strings":["Department of Electrical, Computer, & Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer, & Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056934840","display_name":"Julie Liss","orcid":"https://orcid.org/0000-0001-8782-2901"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie M. Liss","raw_affiliation_strings":["Department of Speech & Hearing Science, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Speech & Hearing Science, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["Department of Electrical, Computer, & Energy Engineering, Arizona State University, Tempe, AZ, USA","Department of Speech & Hearing Science, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer, & Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Department of Speech & Hearing Science, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015429874"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":2.1771,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90411442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2019","issue":null,"first_page":"7315","last_page":"7319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.9980999827384949,"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":0.8308054208755493},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.7497168779373169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.717144787311554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6642634272575378},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6641162633895874},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6544160842895508},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6272647380828857},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5594592690467834},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5404802560806274},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5329822897911072},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5259435772895813},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5147733688354492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5130121111869812},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48858651518821716},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09811457991600037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308054208755493},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.7497168779373169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.717144787311554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6642634272575378},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6641162633895874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6544160842895508},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6272647380828857},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5594592690467834},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5404802560806274},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5329822897911072},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5259435772895813},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5147733688354492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5130121111869812},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48858651518821716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09811457991600037},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:33376454","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33376454","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:arXiv.org:1811.07021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.07021","pdf_url":"https://arxiv.org/pdf/1811.07021","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"},{"id":"pmh:oai:pubmedcentral.nih.gov:7769116","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7769116","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.07021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.07021","pdf_url":"https://arxiv.org/pdf/1811.07021","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W18698765","https://openalex.org/W658020064","https://openalex.org/W1528215465","https://openalex.org/W1614298861","https://openalex.org/W1647671624","https://openalex.org/W1983578042","https://openalex.org/W2046411512","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2251869843","https://openalex.org/W2493916176","https://openalex.org/W2596075132","https://openalex.org/W2605035112","https://openalex.org/W2606699951","https://openalex.org/W2612953412","https://openalex.org/W2752172973","https://openalex.org/W2805328873","https://openalex.org/W2808681756","https://openalex.org/W2887005207","https://openalex.org/W2950577311","https://openalex.org/W2952566282","https://openalex.org/W2962854302","https://openalex.org/W2963336685","https://openalex.org/W2963918774","https://openalex.org/W3104033643","https://openalex.org/W4297699332","https://openalex.org/W6600725435","https://openalex.org/W6621906925","https://openalex.org/W6631825429","https://openalex.org/W6636510571","https://openalex.org/W6636915900","https://openalex.org/W6723250868","https://openalex.org/W6736160952","https://openalex.org/W6743384090","https://openalex.org/W6750372648","https://openalex.org/W6751635672","https://openalex.org/W6752552197"],"related_works":["https://openalex.org/W2379444625","https://openalex.org/W2393147081","https://openalex.org/W2575869988","https://openalex.org/W4308647020","https://openalex.org/W2370088286","https://openalex.org/W2966570129","https://openalex.org/W3099449837","https://openalex.org/W2774861092","https://openalex.org/W4301351852","https://openalex.org/W2622845166"],"abstract_inverted_index":{"A":[0],"key":[1],"initial":[2],"step":[3],"in":[4,120],"several":[5,28,97,138],"natural":[6],"language":[7],"processing":[8],"(NLP)":[9],"tasks":[10,162,186],"involves":[11],"embedding":[12,100,140],"phrases":[13],"of":[14,18,43,64,72,82,137,170],"text":[15,188],"to":[16,114,133,153],"vectors":[17,172],"real":[19],"numbers":[20],"that":[21,26,47,110,145],"preserve":[22],"semantic":[23,38],"meaning.":[24],"To":[25,102],"end,":[27],"methods":[29],"have":[30],"been":[31],"recently":[32],"proposed":[33],"with":[34,175,189],"impressive":[35],"results":[36,143],"on":[37,96,159,183],"similarity":[39,161,185],"tasks.":[40],"However,":[41],"all":[42],"these":[44],"approaches":[45],"assume":[46],"perfect":[48,176],"transcripts":[49],"are":[50,150,165],"available":[51],"when":[52],"generating":[53],"the":[54,80,112,135],"embeddings.":[55],"While":[56],"this":[57,76,131],"is":[58,68],"a":[59,107,121,124],"reasonable":[60],"assumption":[61],"for":[62,70,187],"analysis":[63,71],"written":[65],"text,":[66],"it":[67],"limiting":[69],"transcribed":[73],"text.":[74],"In":[75],"paper":[77],"we":[78,105],"investigate":[79],"effects":[81],"word":[83,117,126,171,190],"substitution":[84,118,191],"errors,":[85],"such":[86],"as":[87],"those":[88],"coming":[89],"from":[90],"automatic":[91],"speech":[92],"recognition":[93],"errors":[94,119,155,164],"(ASR),":[95],"state-of-the-art":[98],"sentence":[99,139,148],"methods.":[101,141],"do":[103],"this,":[104],"propose":[106],"new":[108],"simulator":[109,132],"allows":[111],"experimenter":[113],"induce":[115],"ASR-plausible":[116],"corpus":[122],"at":[123],"desired":[125],"error":[127],"rate.":[128],"We":[129],"use":[130],"evaluate":[134],"robustness":[136],"Our":[142],"show":[144],"pre-trained":[146],"neural":[147],"encoders":[149],"both":[151],"robust":[152],"ASR":[154],"and":[156],"perform":[157,173],"well":[158,174],"textual":[160,184],"after":[163],"introduced.":[166],"Meanwhile,":[167],"unweighted":[168],"averages":[169],"transcriptions,":[177],"but":[178],"their":[179],"performance":[180],"degrades":[181],"rapidly":[182],"errors.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}