{"id":"https://openalex.org/W2889061314","doi":"https://doi.org/10.21437/interspeech.2018-1526","title":"Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment","display_name":"Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889061314","doi":"https://doi.org/10.21437/interspeech.2018-1526","mag":"2889061314"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5113968312","display_name":"Sunit Sivasankaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sunit Sivasankaran","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dominique Fohr","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113968312"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8242,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.86341463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2703","last_page":"2707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.995199978351593,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8289607763290405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7658860683441162},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7471737861633301},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6662306785583496},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.611912727355957},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6003292798995972},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5319887399673462},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.503314197063446},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49309274554252625},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45079049468040466},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.4111565947532654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3412567973136902},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10383462905883789},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09906545281410217},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.07186952233314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289607763290405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7658860683441162},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7471737861633301},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6662306785583496},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.611912727355957},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6003292798995972},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5319887399673462},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.503314197063446},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49309274554252625},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45079049468040466},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.4111565947532654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3412567973136902},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10383462905883789},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09906545281410217},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.07186952233314514},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W1983991597","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W4386900535","https://openalex.org/W2162158162","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Speaker":[0],"localization":[1,55,123],"is":[2],"a":[3,29,37,50,132],"hard":[4],"task,":[5],"especially":[6],"in":[7,42,67,91,134],"adverse":[8,135],"environmental":[9],"conditions":[10,93,139],"involving":[11],"reverberation":[12],"and":[13,57,89,125,137],"noise.":[14],"In":[15],"this":[16,71],"work":[17],"we":[18,126],"introduce":[19],"the":[20,25,33,43,65,84,95,100,106,110,117,121,141],"new":[21],"task":[22],"of":[23,36,45,86,109],"localizing":[24],"speaker":[26,119],"who":[27],"uttered":[28],"given":[30],"keyword,":[31],"e.g.,":[32],"wake-up":[34],"word":[35],"distant-microphone":[38],"voice":[39],"command":[40],"system,":[41],"presence":[44],"overlapping":[46],"speech.":[47,102],"We":[48,73,103],"employ":[49],"convolutional":[51],"neural":[52],"network":[53],"based":[54],"system":[56,66],"investigate":[58],"multiple":[59],"identifiers":[60,79,96],"as":[61],"additional":[62],"inputs":[63],"to":[64,69,116,129],"order":[68],"characterize":[70],"speaker.":[72],"conduct":[74],"experiments":[75],"using":[76,140],"ground":[77,111],"truth":[78,112],"which":[80],"are":[81,97],"obtained":[82],"assuming":[83],"availability":[85],"clean":[87],"speech":[88],"also":[90],"realistic":[92],"where":[94],"computed":[98],"from":[99],"corrupted":[101],"find":[104],"that":[105],"identifier":[107],"consisting":[108],"time-frequency":[113],"mask":[114,133],"corresponding":[115],"target":[118],"provides":[120],"best":[122],"performance":[124],"propose":[127],"methods":[128],"estimate":[130],"such":[131],"reverberant":[136],"noisy":[138],"considered":[142],"keyword.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}