{"id":"https://openalex.org/W2889144942","doi":"https://doi.org/10.21437/interspeech.2018-1547","title":"Monaural Multi-Talker Speech Recognition with Attention Mechanism and Gated Convolutional Networks","display_name":"Monaural Multi-Talker Speech Recognition with Attention Mechanism and Gated Convolutional Networks","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889144942","doi":"https://doi.org/10.21437/interspeech.2018-1547","mag":"2889144942"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1547","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050058892"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4433,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91508036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1586","last_page":"1590"},"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":0.9991000294685364,"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":0.9961000084877014,"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/monaural","display_name":"Monaural","score":0.7848709225654602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7816288471221924},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6278114914894104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6159635186195374},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41651201248168945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.355937123298645},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05171117186546326}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7848709225654602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816288471221924},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6278114914894104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6159635186195374},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41651201248168945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.355937123298645},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05171117186546326},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1547","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1600641642","https://openalex.org/W1600744878","https://openalex.org/W1902237438","https://openalex.org/W2112739286","https://openalex.org/W2144763279","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2188183693","https://openalex.org/W2221409856","https://openalex.org/W2273863404","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2515753980","https://openalex.org/W2515863432","https://openalex.org/W2519224033","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2768808476","https://openalex.org/W2769236969","https://openalex.org/W2796339975","https://openalex.org/W2797187289","https://openalex.org/W2801798988","https://openalex.org/W2804644188","https://openalex.org/W2867138874","https://openalex.org/W2870664433","https://openalex.org/W2879878450","https://openalex.org/W2890505457","https://openalex.org/W2891756742","https://openalex.org/W2892025684","https://openalex.org/W2899771611","https://openalex.org/W2928921291","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W2964308564","https://openalex.org/W3099832538"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1974981856","https://openalex.org/W1983045063","https://openalex.org/W2045506488","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2401567014","https://openalex.org/W2889698889"],"abstract_inverted_index":{"Provided":[0],"are":[1],"a":[2,29],"speech":[3,15,24,37],"recognition":[4,16],"training":[5,17,82,85],"processing":[6,18],"method":[7,19],"and":[8,73],"an":[9,41,75],"apparatus":[10],"including":[11],"the":[12,34,55,64,68,88],"same.":[13],"The":[14],"includes":[20],"acquiring":[21],"multi-talker":[22],"mixed":[23,36],"sequence":[25,38,43],"data":[26,39],"corresponding":[27],"to":[28],"plurality":[30],"of":[31,63],"speakers,":[32],"encoding":[33],"multi-speaker":[35],"into":[40],"embedded":[42,56],"data,":[44],"generating":[45,58],"speaker":[46,65,69],"specific":[47,70],"context":[48,71],"vectors":[49,72],"at":[50],"each":[51,62],"frame":[52],"based":[53,66,86],"on":[54,67,87],"sequence,":[57],"senone":[59,89],"posteriors":[60],"for":[61],"updating":[74],"acoustic":[76],"model":[77,84],"by":[78],"performing":[79],"permutation":[80],"invariant":[81],"(PIT)":[83],"posteriors.":[90]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}