{"id":"https://openalex.org/W137009889","doi":"https://doi.org/10.21437/interspeech.2007-584","title":"Speech-based annotation and retrieval of digital photographs","display_name":"Speech-based annotation and retrieval of digital photographs","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W137009889","doi":"https://doi.org/10.21437/interspeech.2007-584","mag":"137009889"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-584","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy J. Hazen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030942785","display_name":"Brennan P Sherry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brennan Sherry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111980349","display_name":"Mark Adler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Adler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2165","last_page":"2168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12031","display_name":"Speech and dialogue systems","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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.8859473466873169},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6820323467254639},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6687689423561096},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6432238221168518},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6324521899223328},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5527792572975159},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5520768165588379},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5315017104148865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5087211728096008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027902126312256},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44876784086227417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3682861030101776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23015597462654114},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.191117525100708},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12155124545097351},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08668553829193115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8859473466873169},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6820323467254639},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6687689423561096},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6432238221168518},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6324521899223328},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5527792572975159},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5520768165588379},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5315017104148865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5087211728096008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027902126312256},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44876784086227417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3682861030101776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23015597462654114},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.191117525100708},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12155124545097351},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08668553829193115},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-584","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W127628839","https://openalex.org/W183036423","https://openalex.org/W2074892617","https://openalex.org/W2081562286","https://openalex.org/W2105079665","https://openalex.org/W2111732304","https://openalex.org/W2127914268","https://openalex.org/W2159536175","https://openalex.org/W2168037476","https://openalex.org/W2283966783"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2145752793","https://openalex.org/W2131156500","https://openalex.org/W2118916824","https://openalex.org/W1479881079","https://openalex.org/W57476147"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,51],"describe":[4],"the":[5,61],"development":[6],"of":[7,99],"a":[8,20,54,67],"speech-based":[9,49,103],"annotation":[10,104],"and":[11,29,39,43,76,81,105],"retrieval":[12,50,98,106,116],"system":[13,18,64],"for":[14,74,90],"digital":[15],"photographs.":[16],"The":[17],"uses":[19],"client/server":[21],"architecture":[22],"which":[23,59],"allows":[24,60],"photographs":[25,100],"to":[26,65],"be":[27],"captured":[28],"annotated":[30],"on":[31,45],"light-weight":[32],"clients,":[33],"such":[34],"as":[35],"mobile":[36],"camera":[37],"phones,":[38],"then":[40],"processed,":[41],"indexed":[42],"stored":[44],"networked":[46],"servers.":[47],"For":[48],"have":[52],"developed":[53],"mixed":[55],"grammar":[56],"recognition":[57,63],"approach":[58],"speech":[62],"construct":[66],"single":[68],"finite-state":[69],"network":[70],"combining":[71],"context-free":[72],"grammars,":[73],"recognizing":[75,91],"parsing":[77],"query":[78],"carrier":[79],"phrases":[80],"metadata":[82],"phrases,":[83],"with":[84],"an":[85],"unconstrained":[86],"statistical":[87],"n-gram":[88],"model":[89],"free-form":[92],"search":[93],"terms.":[94],"Experiments":[95],"demonstrating":[96],"successful":[97],"using":[101],"purely":[102],"are":[107],"presented.":[108],"Index":[109],"Terms:":[110],"photo":[111],"annotation,":[112],"audio":[113,115],"indexing,":[114]},"counts_by_year":[{"year":2017,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
