{"id":"https://openalex.org/W4392575427","doi":"https://doi.org/10.48550/arxiv.2403.03411","title":"CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation","display_name":"CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation","publication_year":2024,"publication_date":"2024-03-06","ids":{"openalex":"https://openalex.org/W4392575427","doi":"https://doi.org/10.48550/arxiv.2403.03411"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.03411","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03411","pdf_url":"https://arxiv.org/pdf/2403.03411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.03411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009379093","display_name":"Vahid Ahmadi Kalkhorani","orcid":"https://orcid.org/0000-0002-4166-1935","observed_orcids":["https://orcid.org/0000-0002-4166-1935"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kalkhorani, Vahid Ahmadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319","observed_orcids":["https://orcid.org/0000-0001-8195-6319"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, DeLiang","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.986299991607666,"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":0.986299991607666,"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":0.009800000116229057,"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":0.00279999990016222,"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/speaker-separation","display_name":"speaker separation","score":0.8799999952316284},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.7039999961853027},{"id":"https://openalex.org/keywords/multi-head-self-attention","display_name":"multi-head self-attention","score":0.8659999966621399},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.8560000061988831},{"id":"https://openalex.org/keywords/reverberant-speech","display_name":"reverberant speech","score":0.796999990940094},{"id":"https://openalex.org/keywords/noisy-speech","display_name":"noisy speech","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6613677740097046},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6316927671432495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5054488182067871},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.42454177141189575},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.39649301767349243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3448857069015503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15566065907478333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.03411","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03411","pdf_url":"https://arxiv.org/pdf/2403.03411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.03411","doi":"https://doi.org/10.48550/arxiv.2403.03411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.03411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.03411","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03411","pdf_url":"https://arxiv.org/pdf/2403.03411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4804575867","display_name":"Category I: Crossing the Divide Between Today's Practice and Tomorrow's Science","funder_award_id":"2005572","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7332361580","display_name":"Category I: Bridges-2: Scalable Converged Computing, Data, and Analytics for Rapidly Evolving Science and Engineering Research","funder_award_id":"1928147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7975841792","display_name":"Deep Learning Based Complex Spectral Mapping for Multi-Channel Speaker Separation and Speech Enhancement","funder_award_id":"2125074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392575427.pdf","grobid_xml":"https://content.openalex.org/works/W4392575427.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4404102497","https://openalex.org/W4296068589","https://openalex.org/W4404650158","https://openalex.org/W4391621214","https://openalex.org/W7090853379","https://openalex.org/W2892365986","https://openalex.org/W4289110785","https://openalex.org/W4409727705","https://openalex.org/W2968723745","https://openalex.org/W3016094953"],"abstract_inverted_index":{"We":[0],"introduce":[1,59],"CrossNet,":[2,76],"a":[3,25,30,33,60],"complex":[4],"spectral":[5],"mapping":[6],"approach":[7],"to":[8,98,106],"speaker":[9,86],"separation":[10],"and":[11,15,36,44,73,84,92],"enhancement":[12],"in":[13,47,55,80,96,112],"reverberant":[14,83],"noisy":[16],"conditions.":[17],"The":[18],"proposed":[19],"architecture":[20],"comprises":[21],"an":[22,37],"encoder":[23],"layer,":[24],"global":[26],"multi-head":[27],"self-attention":[28],"module,":[29,32,35],"cross-band":[31],"narrow-band":[34,45],"output":[38],"layer.":[39],"CrossNet":[40,89],"captures":[41],"global,":[42],"cross-band,":[43],"correlations":[46],"the":[48,71],"time-frequency":[49],"domain.":[50],"To":[51],"address":[52],"performance":[53,79,104],"degradation":[54],"long":[56],"utterances,":[57],"we":[58],"random":[61],"chunk":[62],"positional":[63],"encoding.":[64],"Experimental":[65],"results":[66],"on":[67],"multiple":[68],"datasets":[69],"demonstrate":[70],"effectiveness":[72],"robustness":[74],"of":[75],"achieving":[77],"state-of-the-art":[78],"tasks":[81],"including":[82],"noisy-reverberant":[85],"separation.":[87],"Furthermore,":[88],"exhibits":[90],"faster":[91],"more":[93],"stable":[94],"training":[95],"comparison":[97],"recent":[99],"baselines.":[100],"Additionally,":[101],"CrossNet's":[102],"high":[103],"extends":[105],"multi-microphone":[107],"conditions,":[108],"demonstrating":[109],"its":[110],"versatility":[111],"various":[113],"acoustic":[114],"scenarios.":[115]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-03-08T00:00:00"}