{"id":"https://openalex.org/W4372259976","doi":"https://doi.org/10.1109/icassp49357.2023.10095413","title":"I See What You Hear: A Vision-Inspired Method to Localize Words","display_name":"I See What You Hear: A Vision-Inspired Method to Localize Words","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259976","doi":"https://doi.org/10.1109/icassp49357.2023.10095413"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095413","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5033081533","display_name":"Mohammad Samragh","orcid":"https://orcid.org/0000-0003-1404-527X"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mohammad Samragh","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034953394","display_name":"Arnav Kundu","orcid":"https://orcid.org/0000-0003-2921-4312"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arnav Kundu","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023750121","display_name":"Ting-Yao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ting-Yao Hu","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047032131","display_name":"Aman Chadha","orcid":"https://orcid.org/0000-0001-6621-9003"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aman Chadha","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051896692","display_name":"Ashish Kumar Srivastava","orcid":"https://orcid.org/0000-0001-9863-528X"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashish Srivastava","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076654","display_name":"Minsik Cho","orcid":"https://orcid.org/0000-0003-0481-2682"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minsik Cho","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028613002","display_name":"Oncel Tuzel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oncel Tuzel","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113880378","display_name":"Devang Naik","orcid":"https://orcid.org/0009-0007-7838-1623"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Devang Naik","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5033081533"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.3962,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53694978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.755005955696106},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7444945573806763},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7058897614479065},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6927607655525208},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.60284823179245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5880632400512695},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5851749777793884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5730823278427124},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5337888598442078},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45669347047805786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3670017421245575},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364967405796051},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.339277982711792},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1231965720653534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755005955696106},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7444945573806763},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7058897614479065},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6927607655525208},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.60284823179245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5880632400512695},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5851749777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730823278427124},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5337888598442078},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45669347047805786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3670017421245575},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364967405796051},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.339277982711792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1231965720653534},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095413","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W1522301498","https://openalex.org/W2144506857","https://openalex.org/W2442329935","https://openalex.org/W2508907749","https://openalex.org/W2747874407","https://openalex.org/W2797583228","https://openalex.org/W2963977978","https://openalex.org/W2964187693","https://openalex.org/W2972476119","https://openalex.org/W3025581723","https://openalex.org/W3093579165","https://openalex.org/W3106250896","https://openalex.org/W3160525311","https://openalex.org/W3163074978","https://openalex.org/W3196496149","https://openalex.org/W3198003134","https://openalex.org/W4225285622","https://openalex.org/W4226033575","https://openalex.org/W4293584584","https://openalex.org/W6631190155","https://openalex.org/W6718561954","https://openalex.org/W6743149223","https://openalex.org/W6750227808","https://openalex.org/W6750665317","https://openalex.org/W6760424586","https://openalex.org/W6784614252","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2095705906","https://openalex.org/W3130645678","https://openalex.org/W2975200075","https://openalex.org/W4285742308","https://openalex.org/W2921865287","https://openalex.org/W2540960825","https://openalex.org/W2732308154","https://openalex.org/W3211653591","https://openalex.org/W1988485990","https://openalex.org/W2801801420"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,24,79,117],"possibility":[4],"of":[5,84],"using":[6],"visual":[7,28],"object":[8,41],"detection":[9,18,62],"techniques":[10,43],"for":[11,27,48,60,70],"word":[12,49,61,71],"localization":[13,42],"in":[14,23,86],"speech":[15],"data.":[16,29],"Object":[17],"has":[19],"been":[20],"thoroughly":[21],"studied":[22],"contemporary":[25],"literature":[26],"Noting":[30],"that":[31],"an":[32],"audio":[33,89],"can":[34,44],"be":[35,45],"interpreted":[36],"as":[37],"a":[38,57,87,97],"1-dimensional":[39],"image,":[40],"fundamentally":[46],"useful":[47],"localization.":[50,64],"Building":[51],"upon":[52],"this":[53],"idea,":[54],"we":[55],"propose":[56],"lightweight":[58],"solution":[59],"and":[63,82,95,115],"We":[65,91],"use":[66],"bounding":[67],"box":[68],"regression":[69],"localization,":[72],"which":[73],"enables":[74],"our":[75,108],"model":[76,98,111],"to":[77,99,104],"detect":[78],"occurrence,":[80],"offset,":[81],"duration":[83],"keywords":[85],"given":[88],"stream.":[90],"experiment":[92],"with":[93],"LibriSpeech":[94],"train":[96],"localize":[100],"1000":[101],"words.":[102],"Compared":[103],"existing":[105],"work":[106],"[1],":[107],"method":[109],"reduces":[110],"size":[112],"by":[113,120],"94%,":[114],"improves":[116],"F1":[118],"score":[119],"6.5%.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}