{"id":"https://openalex.org/W2940826857","doi":"https://doi.org/10.21437/interspeech.2019-1749","title":"SpeechYOLO: Detection and Localization of Speech Objects","display_name":"SpeechYOLO: Detection and Localization of Speech Objects","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2940826857","doi":"https://doi.org/10.21437/interspeech.2019-1749","mag":"2940826857"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1749","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1904.07704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Yael Segal","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","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":false,"raw_author_name":"Tzeviya Sylvia Fuchs","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan 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":["Bar-Ilan University"],"affiliations":[{"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/A5006031844"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":0.5781,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74904914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4210","last_page":"4214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9973999857902527,"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":0.7971644997596741},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6365960240364075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6329187154769897},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6161460280418396},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6070236563682556},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5814667344093323},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5621006488800049},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5414405465126038},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5267851948738098},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48749351501464844},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4410301446914673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0852716863155365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971644997596741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6365960240364075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6329187154769897},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6161460280418396},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6070236563682556},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5814667344093323},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5621006488800049},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5414405465126038},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5267851948738098},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48749351501464844},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4410301446914673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0852716863155365},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1749","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.07704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.07704","pdf_url":"https://arxiv.org/pdf/1904.07704","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:2940826857","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.07704.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.1904.07704","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.07704","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.07704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.07704","pdf_url":"https://arxiv.org/pdf/1904.07704","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2940826857.pdf","grobid_xml":"https://content.openalex.org/works/W2940826857.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2034940213","https://openalex.org/W2037446612","https://openalex.org/W2151244813","https://openalex.org/W2193413348","https://openalex.org/W2407023693","https://openalex.org/W2442329935","https://openalex.org/W2508907749","https://openalex.org/W2520160253","https://openalex.org/W2570343428","https://openalex.org/W2601713192","https://openalex.org/W2747874407","https://openalex.org/W2796347433","https://openalex.org/W2797583228","https://openalex.org/W2899771611","https://openalex.org/W2901891354","https://openalex.org/W2963037989","https://openalex.org/W3106250896","https://openalex.org/W3209382000"],"related_works":["https://openalex.org/W3007167099","https://openalex.org/W3049490129","https://openalex.org/W2801801420","https://openalex.org/W3122675077","https://openalex.org/W2754500569","https://openalex.org/W2734984521","https://openalex.org/W3152844078","https://openalex.org/W2963213879","https://openalex.org/W3004232088","https://openalex.org/W3016205750","https://openalex.org/W2567051930","https://openalex.org/W3211105143","https://openalex.org/W1586079445","https://openalex.org/W2964296749","https://openalex.org/W2964036520","https://openalex.org/W1984924427","https://openalex.org/W2963907377","https://openalex.org/W3046031607","https://openalex.org/W2970910956","https://openalex.org/W2939726645"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,27],"propose":[4],"to":[5,47,57],"apply":[6],"object":[7,38],"detection":[8,39],"methods":[9],"from":[10],"the":[11,15,34,53,78],"vision":[12],"domain":[13],"on":[14,80],"speech":[16,90],"recognition":[17],"domain,":[18],"by":[19,33],"treating":[20],"audio":[21],"fragments":[22],"as":[23],"objects.":[24],"More":[25],"specifically,":[26],"present":[28],"SpeechYOLO,":[29],"which":[30],"is":[31,46,63],"inspired":[32],"YOLO":[35],"algorithm":[36],"for":[37,102],"in":[40],"images.":[41],"The":[42],"goal":[43],"of":[44,50,65,88],"SpeechYOLO":[45],"localize":[48],"boundaries":[49],"utterances":[51],"within":[52],"input":[54],"signal,":[55],"and":[56,91,105],"correctly":[58],"classify":[59],"them.":[60],"Our":[61,94],"system":[62,79,95],"composed":[64],"a":[66,71],"convolutional":[67],"neural":[68],"network,":[69],"with":[70,98],"simple":[72],"least-mean-squares":[73],"loss":[74],"function.":[75],"We":[76],"evaluated":[77],"several":[81],"keyword":[82],"spotting":[83],"tasks,":[84],"that":[85],"include":[86],"corpora":[87],"read":[89],"spontaneous":[92],"speech.":[93],"compares":[96],"favorably":[97],"other":[99],"algorithms":[100],"trained":[101],"both":[103],"localization":[104],"classification.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}