{"id":"https://openalex.org/W2741129224","doi":"https://doi.org/10.1109/sped.2017.7990449","title":"Automatic speaker analysis 2.0: Hearing the bigger picture","display_name":"Automatic speaker analysis 2.0: Hearing the bigger picture","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2741129224","doi":"https://doi.org/10.1109/sped.2017.7990449","mag":"2741129224"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2017.7990449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2017.7990449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["Department of Computing Imperial College, Audeering GMBH, Gilching, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computing Imperial College, Audeering GMBH, Gilching, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043060302"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09536416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.768973171710968},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.6146960258483887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5415963530540466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5152781009674072},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.452159583568573},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4384562075138092},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.43115657567977905},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.426448255777359},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33831408619880676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768973171710968},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.6146960258483887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5415963530540466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5152781009674072},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.452159583568573},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4384562075138092},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.43115657567977905},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.426448255777359},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33831408619880676},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.1109/sped.2017.7990449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2017.7990449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71840","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/71840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W163811496","https://openalex.org/W1574761837","https://openalex.org/W1677182931","https://openalex.org/W1967968483","https://openalex.org/W1975950487","https://openalex.org/W1988596541","https://openalex.org/W2004942499","https://openalex.org/W2015697900","https://openalex.org/W2039846947","https://openalex.org/W2043843997","https://openalex.org/W2045956438","https://openalex.org/W2071843190","https://openalex.org/W2090304207","https://openalex.org/W2127499922","https://openalex.org/W2284916459","https://openalex.org/W2293468623","https://openalex.org/W2325167098","https://openalex.org/W2343758848","https://openalex.org/W2399733683","https://openalex.org/W2402511497","https://openalex.org/W2408690103","https://openalex.org/W2499480874","https://openalex.org/W2533523411","https://openalex.org/W2552261287","https://openalex.org/W2589599921","https://openalex.org/W2598545578","https://openalex.org/W2612919868","https://openalex.org/W2621203830","https://openalex.org/W2735449402","https://openalex.org/W2740375526","https://openalex.org/W2745480282","https://openalex.org/W2746502628","https://openalex.org/W2748699435","https://openalex.org/W2963569749","https://openalex.org/W4244896724","https://openalex.org/W6606699392","https://openalex.org/W6634431961","https://openalex.org/W6647266308","https://openalex.org/W6696967477","https://openalex.org/W6704722722","https://openalex.org/W6712990715","https://openalex.org/W6741967235"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2777500320","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"Automatic":[0,244],"Speaker":[1,245],"Analysis":[2],"has":[3],"largely":[4],"focused":[5],"on":[6,35],"single":[7,38,227],"aspects":[8],"of":[9,27,110,131,134,160,167,191,243],"a":[10,44,59,103,164,226],"speaker":[11,86],"such":[12,96,121,146],"as":[13,97,147],"her":[14,212],"ID,":[15],"gender,":[16],"emotion,":[17],"personality,":[18],"or":[19],"health":[20],"state.":[21],"This":[22],"broadly":[23],"ignores":[24],"the":[25,29,36,64,90,208,217,231,240],"interdependency":[26],"all":[28],"different":[30],"states":[31],"and":[32,61,74,112,123,176,180,211,214,219,234],"traits":[33],"impacting":[34],"one":[37,94],"voice":[39,218],"production":[40],"mechanism":[41],"available":[42],"to":[43,66,82,119,126,169,185,203,206,230,239],"human":[45],"speaker.":[46],"In":[47,137],"other":[48],"words,":[49],"sometimes":[50],"we":[51,56],"may":[52],"sound":[53,75],"depressed,":[54],"but":[55],"simply":[57],"have":[58],"flu,":[60],"hardly":[62],"find":[63],"energy":[65],"put":[67],"more":[68],"vocal":[69],"effort":[70],"into":[71],"our":[72],"articulation":[73],"production.":[76],"Recently,":[77],"this":[78,106,138,140],"lack":[79],"gave":[80],"rise":[81],"an":[83,187],"increasingly":[84],"holistic":[85],"analysis":[87],"-":[88,221],"assessing":[89],"`larger":[91],"picture'":[92],"in":[93,116,163,195],"pass":[95],"by":[98],"multi-target":[99,129,178],"learning.":[100],"However,":[101],"for":[102,155],"robust":[104],"assessment,":[105],"requires":[107],"large":[108,148],"amount":[109],"speech":[111,135,174],"language":[113],"resources":[114],"labelled":[115],"rich":[117,189],"ways":[118],"train":[120],"interdependency,":[122],"architectures":[124],"able":[125],"cope":[127],"with":[128,151],"learning":[130,183],"massive":[132],"amounts":[133],"data.":[136],"light,":[139],"contribution":[141],"will":[142],"discuss":[143],"efficient":[144,177,196],"mechanisms":[145],"socialmedia":[149],"pre-scanning":[150],"dynamic":[152],"cooperative":[153],"crowd-sourcing":[154],"rapid":[156],"data":[157,162],"collection,":[158],"cross-task-labelling":[159],"these":[161],"wider":[165],"range":[166],"attributes":[168],"reach":[170],"`big":[171],"&":[172],"rich'":[173],"data,":[175],"end-to-end":[179],"end-to-evolution":[181],"deep":[182],"paradigms":[184],"learn":[186],"accordingly":[188],"representation":[190],"diverse":[192],"target":[193],"tasks":[194],"ways.":[197],"The":[198],"ultimate":[199],"goal":[200],"behind":[201,216],"is":[202],"enable":[204],"machines":[205],"hear":[207],"`entire'":[209],"person":[210],"condition":[213],"whereabouts":[215],"words":[220],"rather":[222],"than":[223],"aiming":[224],"at":[225],"aspect":[228],"blind":[229],"overall":[232],"individual":[233],"its":[235],"state,":[236],"thus":[237],"leading":[238],"next":[241],"level":[242],"Analysis.":[246]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}