{"id":"https://openalex.org/W2096705927","doi":"https://doi.org/10.1109/icassp.2011.5947388","title":"An approach to sequential grouping in cochannel speech","display_name":"An approach to sequential grouping in cochannel speech","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2096705927","doi":"https://doi.org/10.1109/icassp.2011.5947388","mag":"2096705927"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5110092110","display_name":"Ke Hu","orcid":"https://orcid.org/0009-0003-0835-5893"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Hu","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"4636","last_page":"4639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7857162356376648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7306079864501953},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5535010099411011},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5202211737632751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590406119823456},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.444731742143631},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4224509000778198},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2512158155441284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857162356376648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7306079864501953},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5535010099411011},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5202211737632751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590406119823456},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.444731742143631},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4224509000778198},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2512158155441284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.673","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Hu-Wang.icassp11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W24231854","https://openalex.org/W75206935","https://openalex.org/W140549394","https://openalex.org/W1963835294","https://openalex.org/W1979815907","https://openalex.org/W2013312573","https://openalex.org/W2072184010","https://openalex.org/W2119901478","https://openalex.org/W2136091744","https://openalex.org/W2150269104","https://openalex.org/W2157906748","https://openalex.org/W2159202424","https://openalex.org/W2159591770","https://openalex.org/W2561557072","https://openalex.org/W2981666567","https://openalex.org/W3216401400","https://openalex.org/W4233392025","https://openalex.org/W6603099240","https://openalex.org/W6680180052","https://openalex.org/W6682080839","https://openalex.org/W6769316794","https://openalex.org/W7061955009"],"related_works":["https://openalex.org/W2038216521","https://openalex.org/W2736574136","https://openalex.org/W2565286512","https://openalex.org/W2399955410","https://openalex.org/W3126677997","https://openalex.org/W3129283347","https://openalex.org/W2097377227","https://openalex.org/W2933782699","https://openalex.org/W2565238693","https://openalex.org/W1979706156"],"abstract_inverted_index":{"Model-based":[0],"methods":[1],"for":[2],"sequential":[3,25],"organization":[4,26],"in":[5,108],"cochannel":[6,28],"speech":[7,38,111],"require":[8,88],"pretrained":[9,90],"speaker":[10,41],"models":[11],"and":[12,49,92,97],"often":[13],"prior":[14],"knowledge":[15],"of":[16,27,47,80,110],"participating":[17],"speakers.":[18],"We":[19],"propose":[20],"an":[21,63],"unsupervised":[22],"approach":[23],"to":[24,67],"speech.":[29,83],"Based":[30],"on":[31],"cepstral":[32],"features,":[33],"we":[34,61],"first":[35],"cluster":[36],"voiced":[37,82],"into":[39],"two":[40],"groups":[42],"by":[43,53,76],"maximizing":[44],"the":[45,77,101],"ratio":[46],"between-":[48],"within-group":[50,54],"distances":[51],"penalized":[52],"concurrent":[55],"pitches.":[56],"To":[57],"group":[58],"unvoiced":[59],"speech,":[60],"employ":[62],"onset/offset":[64],"based":[65],"analysis":[66],"generate":[68],"time-frequency":[69],"segments.":[70],"Unvoiced":[71],"segments":[72],"are":[73],"then":[74],"labeled":[75],"complementary":[78],"portions":[79],"segregated":[81],"Our":[84],"method":[85,103,107],"does":[86],"not":[87],"any":[89],"model":[91],"is":[93],"computationally":[94],"simple.":[95],"Evaluations":[96],"comparisons":[98],"show":[99],"that":[100],"proposed":[102],"outperforms":[104],"a":[105],"model-based":[106],"terms":[109],"segregation.":[112]},"counts_by_year":[{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}