{"id":"https://openalex.org/W3135728814","doi":"https://doi.org/10.1109/icassp39728.2021.9414577","title":"CNN-Based Spoken Term Detection and Localization without Dynamic Programming","display_name":"CNN-Based Spoken Term Detection and Localization without Dynamic Programming","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3135728814","doi":"https://doi.org/10.1109/icassp39728.2021.9414577","mag":"3135728814"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414577","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.05468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062227175","display_name":"Tzeviya Sylvia Fuchs","orcid":"https://orcid.org/0000-0002-4666-9346"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Tzeviya Sylvia Fuchs","raw_affiliation_strings":["BarIlan University,Ramat Gan,Israel"],"affiliations":[{"raw_affiliation_string":"BarIlan University,Ramat Gan,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006031844","display_name":"Yael Segal","orcid":"https://orcid.org/0000-0003-2513-0752"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yael Segal","raw_affiliation_strings":["BarIlan University,Ramat Gan,Israel"],"affiliations":[{"raw_affiliation_string":"BarIlan University,Ramat Gan,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["BarIlan University,Ramat Gan,Israel","Bar-Ilan University"],"affiliations":[{"raw_affiliation_string":"BarIlan University,Ramat Gan,Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062227175"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03423659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6853","last_page":"6857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.9986000061035156,"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/term","display_name":"Term (time)","score":0.8098199367523193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.805293083190918},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7484728097915649},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7013448476791382},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6705812811851501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6593693494796753},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6568508744239807},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5922373533248901},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5893312096595764},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5218295454978943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4766555428504944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36025646328926086},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34448373317718506},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32215726375579834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09403306245803833}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.8098199367523193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805293083190918},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7484728097915649},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7013448476791382},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6705812811851501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6593693494796753},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6568508744239807},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5922373533248901},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5893312096595764},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5218295454978943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4766555428504944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36025646328926086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34448373317718506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32215726375579834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09403306245803833},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414577","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"},{"id":"pmh:oai:arXiv.org:2103.05468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.05468","pdf_url":"https://arxiv.org/pdf/2103.05468","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3135728814","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2103.05468","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.2103.05468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.05468","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-journal"},{"id":"doi:10.17023/q6n7-dz48","is_oa":true,"landing_page_url":"https://doi.org/10.17023/q6n7-dz48","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2103.05468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.05468","pdf_url":"https://arxiv.org/pdf/2103.05468","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135728814.pdf","grobid_xml":"https://content.openalex.org/works/W3135728814.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1577418252","https://openalex.org/W1635512741","https://openalex.org/W2052697931","https://openalex.org/W2151244813","https://openalex.org/W2190506272","https://openalex.org/W2399021751","https://openalex.org/W2550241133","https://openalex.org/W2566587499","https://openalex.org/W2747874407","https://openalex.org/W2765122878","https://openalex.org/W2797583228","https://openalex.org/W2888951652","https://openalex.org/W2889270419","https://openalex.org/W2944113786","https://openalex.org/W2962736743","https://openalex.org/W2962835968","https://openalex.org/W2962980711","https://openalex.org/W2963037989","https://openalex.org/W2963777148","https://openalex.org/W2964121744","https://openalex.org/W2972476119","https://openalex.org/W2972592723","https://openalex.org/W3007486152","https://openalex.org/W3106250896","https://openalex.org/W3209382000","https://openalex.org/W6628973269","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6712743090","https://openalex.org/W6731763572","https://openalex.org/W6748326514","https://openalex.org/W6750665317","https://openalex.org/W6752354721","https://openalex.org/W6764726796","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3162022030","https://openalex.org/W2109173967","https://openalex.org/W1487715816","https://openalex.org/W98940168","https://openalex.org/W3134903552","https://openalex.org/W1486671204","https://openalex.org/W2316172020","https://openalex.org/W2059652594","https://openalex.org/W2242808236","https://openalex.org/W2883746099","https://openalex.org/W3167906573","https://openalex.org/W3029661253","https://openalex.org/W1606268232","https://openalex.org/W2178770890","https://openalex.org/W1544896742","https://openalex.org/W2043545441","https://openalex.org/W3150131481","https://openalex.org/W2074382434","https://openalex.org/W1558086160","https://openalex.org/W2737108017"],"abstract_inverted_index":{"In":[0],"this":[1,71],"paper,":[2],"we":[3],"propose":[4],"a":[5,29,34,79],"spoken":[6,111],"term":[7,30,95,112],"detection":[8,113],"algorithm":[9,26,64,86],"for":[10,70,102],"simultaneous":[11],"prediction":[12],"and":[13,17,52,73,96],"localization":[14],"of":[15,45,48,59,92],"in-vocabulary":[16],"out-of-vocabulary":[18],"terms":[19],"within":[20,33],"an":[21,66],"audio":[22],"segment.":[23],"The":[24,63],"proposed":[25],"infers":[27],"whether":[28],"was":[31],"uttered":[32],"given":[35],"speech":[36,50,117],"signal":[37,51],"or":[38],"not":[39,75,98],"by":[40],"predicting":[41],"the":[42,49,56,60,85,93],"word":[43,57],"embeddings":[44],"various":[46],"parts":[47],"comparing":[53],"them":[54],"to":[55,77],"embedding":[58,68,81],"desired":[61],"term.":[62],"utilizes":[65],"existing":[67],"space":[69],"task":[72],"does":[74,97],"need":[76,99],"train":[78],"task-specific":[80],"space.":[82],"At":[83],"inference":[84],"simultaneously":[87],"predicts":[88],"all":[89],"possible":[90],"locations":[91],"target":[94],"dynamic":[100],"programming":[101],"optimal":[103],"search.":[104],"We":[105],"evaluate":[106],"our":[107],"system":[108],"on":[109,115],"several":[110],"tasks":[114],"read":[116],"corpora.":[118]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}