{"id":"https://openalex.org/W2122591647","doi":"https://doi.org/10.1109/icdar.2015.7333812","title":"Towards query-by-speech handwritten keyword spotting","display_name":"Towards query-by-speech handwritten keyword spotting","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2122591647","doi":"https://doi.org/10.1109/icdar.2015.7333812","mag":"2122591647"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2015.7333812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026710474","display_name":"Mar\u00e7al Rusi\u00f1ol","orcid":"https://orcid.org/0000-0002-1734-2205"},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4210134458","display_name":"Institut de Ci\u00e8ncia de Materials de Barcelona","ror":"https://ror.org/03hasqf61","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210134458"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mar\u00e7al Rusi\u00f1ol","raw_affiliation_strings":["Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I4210134458"]},{"raw_affiliation_string":"Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001561491","display_name":"David Aldavert","orcid":"https://orcid.org/0000-0002-9781-9666"},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4210134458","display_name":"Institut de Ci\u00e8ncia de Materials de Barcelona","ror":"https://ror.org/03hasqf61","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210134458"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Aldavert","raw_affiliation_strings":["Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I4210134458"]},{"raw_affiliation_string":"Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009238076","display_name":"Ricardo Toledo","orcid":"https://orcid.org/0000-0001-8113-979X"},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4210134458","display_name":"Institut de Ci\u00e8ncia de Materials de Barcelona","ror":"https://ror.org/03hasqf61","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210134458"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ricardo Toledo","raw_affiliation_strings":["Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I4210134458"]},{"raw_affiliation_string":"Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065907624","display_name":"Josep Llad\u00f3s","orcid":"https://orcid.org/0000-0002-4533-4739"},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4210134458","display_name":"Institut de Ci\u00e8ncia de Materials de Barcelona","ror":"https://ror.org/03hasqf61","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210134458"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Llad\u00f3s","raw_affiliation_strings":["Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Dept. Ci&#x00E8;ncies de la Computaci&#x00F3;, Edifici O, Univ. Aut&#x00F2;noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I4210134458"]},{"raw_affiliation_string":"Computer Vision Center, Dept. Ci\u00e8ncies de la Computaci\u00f3, Edifici O, Univ. Aut\u00f2noma de Barcelona, 08193 Bellaterra (Barcelona), Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.9629238247871399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8897911310195923},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8545486927032471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6160761117935181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5725087523460388},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5367518663406372},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.506492018699646},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4276728630065918},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.42076414823532104},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4188605546951294},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2795908451080322}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9629238247871399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8897911310195923},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8545486927032471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6160761117935181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5725087523460388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5367518663406372},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.506492018699646},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4276728630065918},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.42076414823532104},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4188605546951294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2795908451080322},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1109/icdar.2015.7333812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1606858007","https://openalex.org/W1969408022","https://openalex.org/W1993155451","https://openalex.org/W2027922120","https://openalex.org/W2053317383","https://openalex.org/W2062510230","https://openalex.org/W2062755747","https://openalex.org/W2090861223","https://openalex.org/W2134097102","https://openalex.org/W2137075158","https://openalex.org/W2147152072","https://openalex.org/W2160741934","https://openalex.org/W2162915993","https://openalex.org/W6636412649"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"In":[0,67],"this":[1,92],"paper,":[2],"we":[3],"present":[4,87],"a":[5,27,41,53,82],"new":[6,93],"querying":[7,94],"paradigm":[8],"for":[9],"handwritten":[10,17,83],"keyword":[11,29],"spotting.":[12],"We":[13,86],"propose":[14],"to":[15,40,80],"represent":[16],"word":[18,57],"images":[19],"both":[20],"by":[21,63],"visual":[22,65],"and":[23,38],"audio":[24],"representations,":[25],"enabling":[26],"query-by-speech":[28],"spotting":[30],"system.":[31,85],"The":[32],"two":[33],"representations":[34],"are":[35],"merged":[36],"together":[37],"projected":[39],"common":[42],"sub-space":[43],"in":[44],"the":[45,64,69,100],"training":[46],"phase.":[47],"This":[48],"transform":[49],"allows":[50],"to,":[51],"given":[52],"spoken":[54],"query,":[55],"retrieve":[56],"instances":[58],"that":[59],"were":[60],"only":[61],"represented":[62],"modality.":[66],"addition,":[68],"same":[70],"method":[71],"can":[72],"be":[73],"used":[74],"backwards":[75],"at":[76],"no":[77],"additional":[78],"cost":[79],"produce":[81],"text-to-speech":[84],"our":[88],"first":[89],"results":[90],"on":[91],"mechanism":[95],"using":[96],"synthetic":[97],"voices":[98],"over":[99],"George":[101],"Washington":[102],"dataset.":[103]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
