{"id":"https://openalex.org/W4402111684","doi":"https://doi.org/10.21437/interspeech.2024-1378","title":"Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments","display_name":"Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111684","doi":"https://doi.org/10.21437/interspeech.2024-1378"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1378","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"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":null,"display_name":"Jihyun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihyun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012036252","display_name":"Stijn Kindt","orcid":"https://orcid.org/0000-0001-9300-4251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stijn Kindt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","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":1.2476,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79427695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2185","last_page":"2189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9800999760627747,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9362999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7068561911582947},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5819572806358337},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5646541714668274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4810752868652344},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11562415957450867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.052095502614974976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7068561911582947},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5819572806358337},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5646541714668274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4810752868652344},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11562415957450867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.052095502614974976},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-1378","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01JNDQM899XEK8J33N6HYKSBZJ","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/01JNDQM899XEK8J33N6HYKSBZJ","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4292513318"],"abstract_inverted_index":{"Ad-hoc":[0],"distributed":[1,63,112],"microphone":[2,5,113],"environments,":[3],"where":[4],"locations":[6],"and":[7],"numbers":[8],"are":[9],"unpredictable,":[10],"present":[11],"a":[12],"challenge":[13],"to":[14,29,68,88,103],"traditional":[15],"deep":[16,26,95],"learning":[17,27],"models,":[18],"which":[19],"typically":[20],"require":[21],"fixed":[22],"architectures.":[23],"To":[24],"tailor":[25],"models":[28],"accommodate":[30],"arbitrary":[31],"array":[32],"configurations,":[33],"the":[34,62,77,100,106],"Transform-Average-Concatenate":[35],"(TAC)":[36],"layer":[37],"was":[38],"previously":[39],"introduced.":[40],"In":[41],"this":[42,94],"work,":[43],"we":[44,75],"integrate":[45],"TAC":[46],"layers":[47],"with":[48,105],"dual-path":[49],"transformers":[50],"for":[51],"speech":[52],"separation":[53],"from":[54],"two":[55],"simultaneous":[56],"talkers":[57],"in":[58,110],"realistic":[59],"settings.":[60],"However,":[61],"nature":[64],"makes":[65],"it":[66],"hard":[67],"fuse":[69],"information":[70],"across":[71],"microphones":[72,82],"efficiently.":[73],"Therefore,":[74],"explore":[76],"efficacy":[78],"of":[79,85],"blindly":[80],"clustering":[81],"around":[83],"sources":[84],"interest":[86],"prior":[87],"enhancement.":[89],"Experimental":[90],"results":[91],"show":[92],"that":[93],"cluster-informed":[96],"approach":[97],"significantly":[98],"improves":[99],"system's":[101],"capacity":[102],"cope":[104],"inherent":[107],"variability":[108],"observed":[109],"ad-hoc":[111],"environments.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}