{"id":"https://openalex.org/W2064182530","doi":"https://doi.org/10.1109/slt.2014.7078602","title":"Speaker-independent detection of child-directed speech","display_name":"Speaker-independent detection of child-directed speech","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2064182530","doi":"https://doi.org/10.1109/slt.2014.7078602","mag":"2064182530"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5018467280","display_name":"Sebastian Schuster","orcid":"https://orcid.org/0000-0002-8066-0142"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sebastian Schuster","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA","[Dept. of Comput. Sci., Stanford Univ., CA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Stanford Univ., CA, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045567366","display_name":"Stephanie Pancoast","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Pancoast","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","Department of Electrical Engineering, #R##N#Stanford University, #R##N#CA,#R##N#USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Electrical Engineering, #R##N#Stanford University, #R##N#CA,#R##N#USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076314519","display_name":"Milind Ganjoo","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Ganjoo","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA","[Dept. of Comput. Sci., Stanford Univ., CA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Stanford Univ., CA, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103234894","display_name":"Michael C. Frank","orcid":"https://orcid.org/0000-0002-7551-4378"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael C. Frank","raw_affiliation_strings":["Department of Psychology, Stanford University, Stanford, CA","Department of Psychology, Stanford University, #TAB##TAB##TAB##TAB##TAB##TAB#CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Psychology, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Psychology, Stanford University, #TAB##TAB##TAB##TAB##TAB##TAB#CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA","Dept. of Linguistics, Stanford Univ., CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept. of Linguistics, Stanford Univ., CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018467280"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.8714,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77226941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7833579182624817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6904732584953308},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.624337375164032},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5600225925445557},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4977469742298126},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4906534254550934},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.48266342282295227},{"id":"https://openalex.org/keywords/kurtosis","display_name":"Kurtosis","score":0.47903743386268616},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4511231780052185},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4276588559150696},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4239221215248108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4223596751689911},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4185316562652588},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3886583745479584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33547860383987427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13106870651245117},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10577067732810974},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09214332699775696}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7833579182624817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904732584953308},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.624337375164032},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5600225925445557},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4977469742298126},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4906534254550934},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.48266342282295227},{"id":"https://openalex.org/C166963901","wikidata":"https://www.wikidata.org/wiki/Q287251","display_name":"Kurtosis","level":2,"score":0.47903743386268616},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4511231780052185},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4276588559150696},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4239221215248108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223596751689911},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4185316562652588},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3886583745479584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33547860383987427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13106870651245117},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10577067732810974},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09214332699775696},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2014.7078602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.679.8436","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.679.8436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.stanford.edu/%7Ejurafsky/pubs/slt14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1511187197","https://openalex.org/W1551608136","https://openalex.org/W2001980829","https://openalex.org/W2048843925","https://openalex.org/W2085049476","https://openalex.org/W2090777335","https://openalex.org/W2102040782","https://openalex.org/W2108449190","https://openalex.org/W2120592815","https://openalex.org/W2153647150","https://openalex.org/W2402272953","https://openalex.org/W2607285141","https://openalex.org/W6712741034"],"related_works":["https://openalex.org/W2112649815","https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321"],"abstract_inverted_index":{"Identifying":[0],"the":[1,61,64,84,100],"distinct":[2],"register":[3],"that":[4,26],"adults":[5],"use":[6],"when":[7],"speaking":[8],"to":[9,38],"children":[10],"is":[11],"an":[12],"important":[13],"task":[14],"for":[15],"child":[16],"development":[17],"research.":[18],"We":[19],"present":[20],"a":[21,44,110],"fully":[22],"automatic,":[23],"speaker-independent":[24],"system":[25,32,58],"detects":[27],"child-directed":[28,67],"speech.":[29],"The":[30,57],"two-stage":[31],"uses":[33],"diarization-style":[34],"voice":[35],"activation":[36],"techniques":[37],"extract":[39],"speech":[40,68],"segments":[41],"followed":[42],"by":[43],"supervised":[45],"\u03bd-SVM":[46],"classifier":[47],"trained":[48],"on":[49],"1582":[50],"prosodic":[51],"and":[52,75,92,103],"log":[53,106],"Mel":[54,107],"energy":[55,108],"features.":[56],"significantly":[59],"improves":[60],"state":[62],"of":[63,71,86,105],"art,":[65],"detecting":[66],"with":[69],"F1":[70],".66":[72],"(exact":[73],"boundary)":[74],".83":[76],"(within":[77],"1":[78],"second).":[79],"A":[80],"feature":[81],"analysis":[82],"confirms":[83],"importance":[85],"F0":[87],"features":[88,98],"(especially":[89],"3rd":[90],"quartile":[91],"range)":[93],"as":[94,96],"well":[95],"new":[97],"like":[99],"variance,":[101],"kurtosis,":[102],"min":[104],"within":[109],"frequency":[111],"band.":[112]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
