{"id":"https://openalex.org/W4416798748","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249139","title":"Speaker Localization in Classroom Environments Using GCC-PHAT Features and Mamba State Space Models with Ad-Hoc Microphone Arrays","display_name":"Speaker Localization in Classroom Environments Using GCC-PHAT Features and Mamba State Space Models with Ad-Hoc Microphone Arrays","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798748","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249139"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5053298892","display_name":"Rashed Iqbal","orcid":"https://orcid.org/0000-0002-6741-1846"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rashed Iqbal","raw_affiliation_strings":["University of Wollongong,NSW,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong,NSW,Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033818201","display_name":"Christian Ritz","orcid":"https://orcid.org/0000-0002-3768-7569"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christian Ritz","raw_affiliation_strings":["University of Wollongong,NSW,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong,NSW,Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jack Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jack Yang","raw_affiliation_strings":["University of Wollongong,NSW,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong,NSW,Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006168870","display_name":"Sarah Howard","orcid":"https://orcid.org/0000-0002-9690-2134"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sarah Howard","raw_affiliation_strings":["University of Leeds,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds,UK","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3931693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9437999725341797,"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":0.9437999725341797,"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":0.01720000058412552,"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":0.013799999840557575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7300000190734863},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7014999985694885},{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.6189000010490417},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.38530001044273376},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7300000190734863},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7014999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230000257492065},{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.6189000010490417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.375},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.33899998664855957},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1510862346","https://openalex.org/W2107321726","https://openalex.org/W2113638573","https://openalex.org/W2151227854","https://openalex.org/W2763188033","https://openalex.org/W2765962757","https://openalex.org/W2772734659","https://openalex.org/W2772736377","https://openalex.org/W2776323726","https://openalex.org/W2964342924","https://openalex.org/W2997884353","https://openalex.org/W3081461453","https://openalex.org/W3117498573","https://openalex.org/W4221162997","https://openalex.org/W4312120798","https://openalex.org/W4372346491","https://openalex.org/W4385822984","https://openalex.org/W4391266307","https://openalex.org/W4392122702","https://openalex.org/W4406858736","https://openalex.org/W4408354310","https://openalex.org/W4408355587","https://openalex.org/W4409921806","https://openalex.org/W4410087476","https://openalex.org/W4410369930","https://openalex.org/W4415433692"],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"understanding":[1],"classroom":[2,28,83],"interactions":[3],"is":[4],"essential":[5],"for":[6,24,51,66],"assessing":[7],"teaching":[8],"quality":[9],"and":[10,59,88,94,97,111,131],"student":[11],"engagement.":[12],"This":[13],"study":[14],"presents":[15],"a":[16,92],"novel":[17],"audio-only":[18],"source":[19],"localization":[20],"(SSL)":[21],"framework":[22],"designed":[23],"locating":[25],"speakers":[26],"within":[27],"environments":[29,84],"using":[30],"two":[31,100],"microphone":[32,102],"arrays":[33,110],"located":[34],"at":[35],"unknown":[36],"locations":[37],"in":[38,125],"the":[39,60],"room.":[40],"The":[41],"proposed":[42],"method":[43],"integrates":[44],"Generalized":[45],"Cross-Correlation":[46],"with":[47,99],"Phase":[48],"Transform":[49],"(GCCPHAT)":[50],"time":[52],"difference":[53],"of":[54,75,85],"arrival":[55],"(TDOA)":[56],"feature":[57],"extraction":[58],"Mamba":[61],"State":[62],"Space":[63],"Model":[64],"(SSM)":[65],"sequence":[67],"modelling":[68],"to":[69,80],"estimate":[70],"speaker":[71],"locations.":[72],"A":[73],"dataset":[74],"reverberant":[76],"speech":[77],"recordings":[78],"corresponding":[79],"three":[81],"simulated":[82],"different":[86,101],"size":[87],"reverberation":[89],"levels":[90],"containing":[91],"teacher":[93],"multiple":[95],"students":[96],"recorded":[98],"setups,":[103],"including":[104],"First":[105],"Order":[106],"Ambisonic":[107],"(FOA)":[108],"Bformat":[109],"6-channel":[112],"circular":[113],"arrays.":[114],"Experimental":[115],"results":[116],"demonstrate":[117],"that":[118],"our":[119],"approach":[120],"significantly":[121],"outperforms":[122],"conventional":[123],"baselines":[124],"both":[126],"Mean":[127,132],"Angular":[128],"Error":[129,134],"(MAE)":[130],"Distance":[133],"(MDE).":[135]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}