{"id":"https://openalex.org/W3047219644","doi":"https://doi.org/10.21437/interspeech.2020-2822","title":"\u201cThis is Houston. Say again, please\u201d. The Behavox System for the Apollo-11 Fearless Steps Challenge (Phase II)","display_name":"\u201cThis is Houston. Say again, please\u201d. The Behavox System for the Apollo-11 Fearless Steps Challenge (Phase II)","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047219644","doi":"https://doi.org/10.21437/interspeech.2020-2822","mag":"3047219644"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2822","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2008.01504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002166593","display_name":"Arseniy Gorin","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Arseniy Gorin","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027835976","display_name":"Daniil Kulko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniil Kulko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023902755","display_name":"Steven Grima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Grima","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057641344","display_name":"Alex Glasman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Glasman","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002166593"],"corresponding_institution_ids":["https://openalex.org/I277688954"],"apc_list":null,"apc_paid":null,"fwci":0.14685955,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53928766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"2612","last_page":"2616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9908999800682068,"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":0.7780240774154663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6489421129226685},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6121978163719177},{"id":"https://openalex.org/keywords/apollo","display_name":"Apollo","score":0.6004571914672852},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5395371913909912},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5260065793991089},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5232607126235962},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.514612078666687},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4422316253185272},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4332975447177887},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4220028221607208},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4171541631221771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4066847860813141},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38574880361557007},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.1791347861289978},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12911665439605713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780240774154663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6489421129226685},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6121978163719177},{"id":"https://openalex.org/C2779821442","wikidata":"https://www.wikidata.org/wiki/Q41633","display_name":"Apollo","level":2,"score":0.6004571914672852},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5395371913909912},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5260065793991089},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5232607126235962},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.514612078666687},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4422316253185272},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4332975447177887},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4220028221607208},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4171541631221771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4066847860813141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38574880361557007},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.1791347861289978},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12911665439605713},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C90856448","wikidata":"https://www.wikidata.org/wiki/Q431","display_name":"Zoology","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2822","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.01504","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.01504","pdf_url":"https://arxiv.org/pdf/2008.01504","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3047219644","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.01504.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.2008.01504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.01504","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.01504","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.01504","pdf_url":"https://arxiv.org/pdf/2008.01504","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047219644.pdf","grobid_xml":"https://content.openalex.org/works/W3047219644.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1965819578","https://openalex.org/W1975113979","https://openalex.org/W2079623482","https://openalex.org/W2090755665","https://openalex.org/W2096702961","https://openalex.org/W2395659169","https://openalex.org/W2400997536","https://openalex.org/W2406262283","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2746887616","https://openalex.org/W2802422770","https://openalex.org/W2888867175","https://openalex.org/W2889041236","https://openalex.org/W2889418727","https://openalex.org/W2890569262","https://openalex.org/W2890964092","https://openalex.org/W2914018192","https://openalex.org/W2939777153","https://openalex.org/W2954461214","https://openalex.org/W2972680151","https://openalex.org/W2972869740","https://openalex.org/W2981103786","https://openalex.org/W3015544392","https://openalex.org/W3017144692","https://openalex.org/W3097636940","https://openalex.org/W3101648800"],"related_works":["https://openalex.org/W3097257401","https://openalex.org/W3147962056","https://openalex.org/W2177420620","https://openalex.org/W2899439440","https://openalex.org/W2093392830","https://openalex.org/W3148272037","https://openalex.org/W3004597053","https://openalex.org/W2939069254","https://openalex.org/W2790982786","https://openalex.org/W2080141381","https://openalex.org/W3015810689","https://openalex.org/W2163592168","https://openalex.org/W1598429815","https://openalex.org/W2189369791","https://openalex.org/W1982353852","https://openalex.org/W2397133385","https://openalex.org/W5769393","https://openalex.org/W2106472082","https://openalex.org/W2079542053","https://openalex.org/W2047542028"],"abstract_inverted_index":{"We":[0,114],"describe":[1],"the":[2,18,22,55,72,110,124,129,161,179],"speech":[3,12],"activity":[4],"detection":[5],"(SAD),":[6],"speaker":[7,149],"diarization":[8,134],"(SD),":[9],"and":[10,41,46,94,119,135,165,172,174],"automatic":[11],"recognition":[13],"(ASR)":[14],"experiments":[15],"conducted":[16],"by":[17],"Behavox":[19],"team":[20],"for":[21,88,133,144,170,176],"Interspeech":[23],"2020":[24],"Fearless":[25],"Steps":[26],"Challenge":[27],"(FSC-2).":[28],"A":[29],"relatively":[30],"small":[31],"amount":[32],"of":[33,39,67,91,128],"labeled":[34],"data,":[35],"a":[36,75,167],"large":[37],"variety":[38],"speakers":[40],"channel":[42],"distortions,":[43],"specific":[44],"lexicon":[45],"speaking":[47],"style":[48],"resulted":[49],"in":[50,178],"high":[51],"error":[52,103],"rates":[53],"on":[54,109],"systems":[56,121],"which":[57],"involved":[58],"this":[59],"data.":[60],"In":[61],"addition":[62],"to":[63,107,122,160],"approximately":[64],"36":[65],"hours":[66],"annotated":[68],"NASA":[69],"mission":[70],"recordings,":[71],"organizers":[73],"provided":[74,143],"much":[76],"larger":[77],"but":[78],"unlabeled":[79],"19k":[80],"hour":[81],"Apollo-11":[82],"corpus":[83],"that":[84],"we":[85,154],"also":[86,115],"explore":[87],"semi-supervised":[89],"training":[90,108],"ASR":[92,173],"acoustic":[93],"language":[95],"models,":[96],"observing":[97],"more":[98],"than":[99],"17%":[100],"relative":[101],"word":[102],"rate":[104],"improvement":[105],"compared":[106,159],"FSC-2":[111,162],"data":[112],"only.":[113],"compare":[116],"several":[117],"SAD":[118,177],"SD":[120,171],"approach":[123],"most":[125],"difficult":[126],"tracks":[127],"challenge":[130],"(track":[131],"1":[132],"ASR),":[136],"where":[137],"long":[138],"30-minute":[139],"audio":[140],"recordings":[141],"are":[142],"evaluation":[145],"without":[146],"segmentation":[147],"or":[148],"information.":[150],"For":[151],"all":[152],"systems,":[153,164],"report":[155],"substantial":[156],"performance":[157],"improvements":[158],"baseline":[163],"achieved":[166],"first-place":[168],"ranking":[169],"fourth-place":[175],"challenge.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}