{"id":"https://openalex.org/W2118333821","doi":"https://doi.org/10.21437/interspeech.2004-433","title":"The audio-video australian English speech data corpus AVOZES","display_name":"The audio-video australian English speech data corpus AVOZES","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W2118333821","doi":"https://doi.org/10.21437/interspeech.2004-433","mag":"2118333821"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-433","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5006870349","display_name":"J. Bruce Millar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Bruce Millar","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046144886","display_name":"Roland Goecke","orcid":"https://orcid.org/0000-0003-2279-7041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roland Goecke","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8909,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.94799761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2525","last_page":"2528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9803000092506409,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.974399983882904,"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":0.8253303170204163},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6619648933410645},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5789868831634521},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5687961578369141},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.48538362979888916},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.48331522941589355},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44482171535491943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4143187999725342},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4119483232498169},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3965557813644409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36339646577835083},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2557663917541504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253303170204163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6619648933410645},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5789868831634521},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5687961578369141},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.48538362979888916},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.48331522941589355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44482171535491943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4143187999725342},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4119483232498169},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3965557813644409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36339646577835083},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2557663917541504},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-433","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.587.9401","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.587.9401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cecs.anu.edu.au/~bruce/papers/pdf/GoeckeMillarAvozes.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W7512398","https://openalex.org/W22517275","https://openalex.org/W98035269","https://openalex.org/W121156950","https://openalex.org/W1251982623","https://openalex.org/W1490482062","https://openalex.org/W1514860245","https://openalex.org/W1527240141","https://openalex.org/W1549965231","https://openalex.org/W1555614281","https://openalex.org/W1598123022","https://openalex.org/W1607942592","https://openalex.org/W1731103611","https://openalex.org/W1893902159","https://openalex.org/W2004826498","https://openalex.org/W2026028405","https://openalex.org/W2098923380","https://openalex.org/W2115797648","https://openalex.org/W2122928074","https://openalex.org/W2131874588","https://openalex.org/W2142518644","https://openalex.org/W2145224127","https://openalex.org/W2145713909","https://openalex.org/W2146824864","https://openalex.org/W3099202502"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W1987021544","https://openalex.org/W2022789108","https://openalex.org/W2009814707"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,29,59,81],"Audio-Video":[4],"Australian":[5,67],"English":[6,68],"Speech":[7],"data":[8,64],"corpus":[9,23,65],"AVOZES.":[10],"It":[11],"contains":[12],"recordings":[13,83],"of":[14,20,32,75],"20":[15],"speakers":[16],"ut-tering":[17],"a":[18,76],"variety":[19],"phrases.":[21],"The":[22],"was":[24],"designed":[25],"for":[26,53,66,80],"re-search":[27],"on":[28],"statistical":[30],"relationship":[31],"audio":[33],"and":[34,69,84],"video":[35,82],"speech":[36,43],"parameters":[37],"with":[38],"an":[39],"audio-video":[40],"(AV)":[41],"automatic":[42],"recog-nition":[44],"(ASR)":[45],"task":[46],"in":[47,72],"mind,":[48],"but":[49],"may":[50],"be":[51],"useful":[52],"other":[54],"research":[55],"tasks.":[56],"AVOZES":[57],"is":[58,70],"first":[60],"published":[61],"AV":[62],"speaking-face":[63],"novel":[71],"its":[73,85],"use":[74],"stereo":[77],"camera":[78],"system":[79],"modular":[86],"design.":[87],"1.":[88]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
