{"id":"https://openalex.org/W2626463069","doi":"https://doi.org/10.21437/interspeech.2017-1592","title":"Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings","display_name":"Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2626463069","doi":"https://doi.org/10.21437/interspeech.2017-1592","mag":"2626463069"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1592","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1706.03818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007445208","display_name":"Shane Settle","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shane Settle","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112870105","display_name":"Keith Levin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keith Levin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007445208"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7476,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70514661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2874","last_page":"2878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8420902490615845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.765724778175354},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6961873173713684},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6820213794708252},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5794380307197571},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5646131038665771},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5220610499382019},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.51652592420578},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46401867270469666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45366814732551575},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4467582404613495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3707064986228943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14217036962509155}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8420902490615845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765724778175354},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6961873173713684},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6820213794708252},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5794380307197571},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5646131038665771},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5220610499382019},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.51652592420578},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46401867270469666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45366814732551575},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4467582404613495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3707064986228943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14217036962509155},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-1592","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1706.03818","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.03818","pdf_url":"https://arxiv.org/pdf/1706.03818","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":"mag:2626463069","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1706.03818.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1706.03818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1706.03818","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1706.03818","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.03818","pdf_url":"https://arxiv.org/pdf/1706.03818","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":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2626463069.pdf","grobid_xml":"https://content.openalex.org/works/W2626463069.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1522301498","https://openalex.org/W1545920196","https://openalex.org/W1577418252","https://openalex.org/W1967924372","https://openalex.org/W2012833704","https://openalex.org/W2059652594","https://openalex.org/W2064675550","https://openalex.org/W2074932712","https://openalex.org/W2097308346","https://openalex.org/W2110625382","https://openalex.org/W2126203737","https://openalex.org/W2127589108","https://openalex.org/W2147717514","https://openalex.org/W2149557440","https://openalex.org/W2166637769","https://openalex.org/W2166778951","https://openalex.org/W2171019095","https://openalex.org/W2187089797","https://openalex.org/W2190506272","https://openalex.org/W2291770225","https://openalex.org/W2295297373","https://openalex.org/W2402401665","https://openalex.org/W2407151108","https://openalex.org/W2550241133","https://openalex.org/W2951216052","https://openalex.org/W2963311389"],"related_works":["https://openalex.org/W2962980711","https://openalex.org/W2963680465","https://openalex.org/W2510769428","https://openalex.org/W2466445867","https://openalex.org/W2792374636","https://openalex.org/W2916450621","https://openalex.org/W3096708513","https://openalex.org/W2007597876","https://openalex.org/W3168078812","https://openalex.org/W2585485150","https://openalex.org/W309286","https://openalex.org/W2003340926","https://openalex.org/W2963542658","https://openalex.org/W2397291310","https://openalex.org/W3170018863","https://openalex.org/W2148291820","https://openalex.org/W1991584419","https://openalex.org/W2100839471","https://openalex.org/W2618114732","https://openalex.org/W3162036289"],"abstract_inverted_index":{"Query-by-example":[0],"search":[1,57,74],"often":[2],"uses":[3],"dynamic":[4],"time":[5],"warping":[6],"(DTW)":[7],"for":[8],"comparing":[9,20],"queries":[10],"and":[11,34,63,113],"proposed":[12],"matching":[13,78],"segments.":[14,79],"Recent":[15],"work":[16,81],"has":[17],"shown":[18],"that":[19,58,95],"speech":[21],"segments":[22,65],"by":[23,72],"representing":[24],"them":[25],"as":[26],"fixed-dimensional":[27],"vectors":[28],"---":[29,33],"acoustic":[30,87],"word":[31,88,106],"embeddings":[32],"measuring":[35],"their":[36],"vector":[37],"distance":[38],"(e.g.,":[39],"cosine":[40],"distance)":[41],"can":[42],"discriminate":[43],"between":[44],"words":[45],"more":[46],"accurately":[47],"than":[48],"DTW-based":[49],"approaches.":[50,119],"We":[51,93],"consider":[52],"an":[53],"approach":[54],"to":[55,67,75,104],"query-by-example":[56],"embeds":[59],"both":[60],"the":[61,77,117],"query":[62],"database":[64],"according":[66],"a":[68],"neural":[69,101],"model,":[70],"followed":[71],"nearest-neighbor":[73],"find":[76,94],"Earlier":[80],"on":[82,99],"embedding-based":[83],"query-by-example,":[84],"using":[85],"template-based":[86],"embeddings,":[89,97],"achieved":[90],"competitive":[91],"performance.":[92],"our":[96],"based":[98],"recurrent":[100],"networks":[102],"trained":[103],"optimize":[105],"discrimination,":[107],"achieve":[108],"substantial":[109],"improvements":[110],"in":[111],"performance":[112],"run-time":[114],"efficiency":[115],"over":[116],"previous":[118]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}