{"id":"https://openalex.org/W2149648698","doi":"https://doi.org/10.21437/interspeech.2006-25","title":"Super-human multi-talker speech recognition: the IBM 2006 speech separation challenge system","display_name":"Super-human multi-talker speech recognition: the IBM 2006 speech separation challenge system","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W2149648698","doi":"https://doi.org/10.21437/interspeech.2006-25","mag":"2149648698"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-25","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5056600749","display_name":"T. Kristjansson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Kristjansson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112154658","display_name":"J. Hershey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Hershey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037212510","display_name":"Peder A. Olsen","orcid":"https://orcid.org/0000-0002-3836-8017"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Olsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088753951","display_name":"Steven J. Rennie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Rennie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103606070","display_name":"Ramesh A. Gopinath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramesh Gopinath","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":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1775","last_page":"Mon1WeS.7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9951000213623047,"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/speech-recognition","display_name":"Speech recognition","score":0.786594033241272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309907078742981},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6932182312011719},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4640952944755554},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4556678831577301},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.43229836225509644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3271680474281311},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0601942241191864}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.786594033241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309907078742981},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6932182312011719},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4640952944755554},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4556678831577301},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.43229836225509644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3271680474281311},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0601942241191864},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2006-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-25","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.4496","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.4496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~martin/SpeechSeparationChallenge/kristjansson_june.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.131.5330","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.131.5330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~martin/SpeechSeparationChallenge/kristjansson.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W123512928","https://openalex.org/W1800365115","https://openalex.org/W2100969003","https://openalex.org/W2170256193"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W3135230428","https://openalex.org/W2164637175","https://openalex.org/W2603275087","https://openalex.org/W2099105119","https://openalex.org/W2069501481","https://openalex.org/W3002577753","https://openalex.org/W2182174551","https://openalex.org/W2141919489","https://openalex.org/W2149648698"],"abstract_inverted_index":{"We":[0,51,66],"describe":[1],"a":[2,31,40],"system":[3,22],"for":[4,43,71],"model":[5,56,81],"based":[6,57,87],"speech":[7,26],"separation":[8,102],"which":[9],"achieves":[10],"super-human":[11],"recognition":[12],"performance":[13],"when":[14],"two":[15,28,69],"talkers":[16],"speak":[17],"at":[18],"similar":[19],"levels.":[20],"The":[21,91],"can":[23],"separate":[24],"the":[25,53,74,79,83,101,105],"of":[27,55,93],"speakers":[29],"from":[30],"single":[32],"channel":[33],"recording":[34],"with":[35],"remarkable":[36],"results.":[37],"It":[38],"incorporates":[39,85],"novel":[41],"method":[42,54],"performing":[44],"two-talker":[45],"speaker":[46,115],"identification":[47],"and":[48],"gain":[49],"estimation.":[50],"extend":[52],"high":[58],"resolution":[59],"signal":[60],"reconstruction":[61],"to":[62,97],"incorporate":[63],"temporal":[64,94],"dynamics.":[65],"report":[67],"on":[68,88],"methods":[70],"introducing":[72],"dynamics;":[73],"first":[75],"uses":[76],"dynamics":[77,86],"in":[78,100],"acoustic":[80],"space,":[82],"second":[84],"sentence":[89],"grammar.":[90],"addition":[92],"constraints":[95],"leads":[96],"dramatic":[98],"improvements":[99],"performance.":[103],"Once":[104],"signals":[106],"have":[107],"been":[108],"separated":[109],"they":[110],"are":[111],"then":[112],"recognized":[113],"using":[114],"dependent":[116],"labeling.":[117],"1.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
