{"id":"https://openalex.org/W62694336","doi":"https://doi.org/10.21437/interspeech.2005-483","title":"Modeling the perception of multitalker speech","display_name":"Modeling the perception of multitalker speech","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W62694336","doi":"https://doi.org/10.21437/interspeech.2005-483","mag":"62694336"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-483","doi":"https://doi.org/10.21437/interspeech.2005-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-483","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},"volume":null,"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/A5102163048","display_name":"Soundararajan Srinivasan","orcid":"https://orcid.org/0009-0004-0842-7743","observed_orcids":["https://orcid.org/0009-0004-0842-7743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soundararajan Srinivasan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319","observed_orcids":["https://orcid.org/0000-0001-8195-6319"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","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":1.5934,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81293392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1265","last_page":"1268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5884000062942505,"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":0.5884000062942505,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.4004000127315521,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/energetic-masking","display_name":"energetic masking","score":0.949999988079071},{"id":"https://openalex.org/keywords/informational-masking","display_name":"informational masking","score":1.0},{"id":"https://openalex.org/keywords/speech-segregation","display_name":"speech segregation","score":0.7459999918937683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7070000171661377},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.5839999914169312},{"id":"https://openalex.org/keywords/time-frequency-masking","display_name":"time-frequency masking","score":0.6620000004768372},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"auditory scene analysis","score":0.640999972820282}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.9032981395721436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7384803295135498},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.736916184425354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214353084564209},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5531599521636963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3383484482765198},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1128796935081482},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07977294921875},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2005-483","doi":"https://doi.org/10.21437/interspeech.2005-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-483","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.123.3783","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.123.3783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Sriniv-Wang.is05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W133022121","https://openalex.org/W293155492","https://openalex.org/W1575829986","https://openalex.org/W1991112797","https://openalex.org/W2013020033","https://openalex.org/W2034040413","https://openalex.org/W2044222806","https://openalex.org/W2046058153","https://openalex.org/W2057889776","https://openalex.org/W2074354966","https://openalex.org/W2080921589","https://openalex.org/W2106981472","https://openalex.org/W2149425615","https://openalex.org/W2338272569","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W2059250847","https://openalex.org/W2094427326","https://openalex.org/W1487965229","https://openalex.org/W2025413813","https://openalex.org/W2057889776","https://openalex.org/W1982070155","https://openalex.org/W4250500702","https://openalex.org/W1991112797","https://openalex.org/W4385823127","https://openalex.org/W2187204608"],"abstract_inverted_index":{"Listeners":[0],"\u2019":[1],"ability":[2],"to":[3,20,56],"understand":[4],"a":[5,68,92,120,125],"target":[6,32,45,59,102],"speaker":[7],"in":[8,37,42,83,135],"the":[9,52,58,84,97,112,117,128,131],"presence":[10,85],"of":[11,23,44,70,79,86,101,108,119,130],"one":[12],"or":[13],"more":[14],"simultaneous":[15],"competing":[16],"speakers":[17],"is":[18,54,89,134],"subject":[19],"two":[21],"types":[22,78],"masking:":[24],"Energetic":[25,28],"and":[26,33,39],"informational.":[27],"masking":[29,49,88,110],"occurs":[30,50],"when":[31,51],"interfering":[34],"signals":[35],"overlap":[36],"time":[38],"frequency":[40],"resulting":[41],"portions":[43],"becoming":[46],"inaudible.":[47],"Informational":[48],"listener":[53],"unable":[55],"segregate":[57],"from":[60],"interference,":[61],"while":[62],"both":[63,77],"are":[64,114],"audible.":[65],"We":[66],"present":[67],"model":[69,133],"multitalker":[71],"speech":[72,93,121],"perception":[73,82],"that":[74,95],"accounts":[75],"for":[76],"masking.":[80],"Human":[81],"energetic":[87],"modeled":[90,115],"using":[91,116],"recognizer":[94,113],"treats":[96],"masked":[98],"time-frequency":[99],"units":[100],"as":[103],"missing":[104],"data.":[105],"The":[106],"effects":[107],"informational":[109],"on":[111],"output":[118],"segregation":[122],"system.":[123],"On":[124],"systematic":[126],"evaluation,":[127],"performance":[129],"proposed":[132],"broad":[136],"agreement":[137],"with":[138],"perceptual":[139],"results.":[140],"1.":[141]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}
