{"id":"https://openalex.org/W4226058124","doi":"https://doi.org/10.1109/asru51503.2021.9688078","title":"Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation","display_name":"Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226058124","doi":"https://doi.org/10.1109/asru51503.2021.9688078"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688078","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100672354","display_name":"Qinglin Zhang","orcid":"https://orcid.org/0009-0006-3647-8470"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qinglin Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346266","display_name":"Yali Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yali Li","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949746","display_name":"Jiaqing Liu","orcid":"https://orcid.org/0000-0001-8600-8932"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Liu","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab","Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100672354"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.8796,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.78519349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T13629","display_name":"Text Readability and Simplification","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489884734153748},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7218446731567383},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7088242769241333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6450840830802917},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5852377414703369},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5649169683456421},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5645017623901367},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5600265860557556},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5206927061080933},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48739463090896606},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.45375561714172363},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4295494854450226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.17280614376068115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489884734153748},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7218446731567383},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7088242769241333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450840830802917},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5852377414703369},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5649169683456421},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5645017623901367},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5600265860557556},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5206927061080933},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48739463090896606},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.45375561714172363},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4295494854450226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.17280614376068115},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688078","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W145178388","https://openalex.org/W1522301498","https://openalex.org/W1626209120","https://openalex.org/W1626945812","https://openalex.org/W1983814883","https://openalex.org/W2080179128","https://openalex.org/W2100873065","https://openalex.org/W2149367074","https://openalex.org/W2512217112","https://openalex.org/W2525778437","https://openalex.org/W2793710388","https://openalex.org/W2807938752","https://openalex.org/W2896457183","https://openalex.org/W2962716111","https://openalex.org/W2965373594","https://openalex.org/W2995923603","https://openalex.org/W2997244287","https://openalex.org/W3035027743","https://openalex.org/W3102373121","https://openalex.org/W4287824654","https://openalex.org/W6605854414","https://openalex.org/W6631190155","https://openalex.org/W6636660855","https://openalex.org/W6636730337","https://openalex.org/W6670669346","https://openalex.org/W6749811377","https://openalex.org/W6751906393","https://openalex.org/W6755207826","https://openalex.org/W6766668698","https://openalex.org/W6766673545","https://openalex.org/W6771825421","https://openalex.org/W6771917389"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2032810564","https://openalex.org/W2370831213","https://openalex.org/W2972807713","https://openalex.org/W4315704968","https://openalex.org/W2100255360","https://openalex.org/W2107506952","https://openalex.org/W3135287016"],"abstract_inverted_index":{"Transcripts":[0],"generated":[1],"by":[2,123,130],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"systems":[7],"for":[8,25,52],"spoken":[9,26,72,100],"documents":[10,27],"lack":[11],"structural":[12],"annotations":[13],"such":[14,36],"as":[15,37],"paragraphs,":[16],"significantly":[17,68],"reducing":[18,134],"their":[19],"readability.":[20],"Automatically":[21],"predicting":[22],"paragraph":[23,56],"segmentation":[24,74,92,117],"may":[28],"both":[29],"improve":[30],"readability":[31],"and":[32,39,54,96,126],"downstream":[33],"NLP":[34],"performance":[35],"summarization":[38],"machine":[40],"reading":[41],"comprehension.":[42],"We":[43,58],"propose":[44,60],"a":[45,88],"sequence":[46],"model":[47,105,110],"with":[48],"self-adaptive":[49],"sliding":[50],"window":[51],"accurate":[53],"efficient":[55],"segmentation.":[57],"also":[59],"an":[61,97],"approach":[62],"to":[63,75,137],"exploit":[64],"pho-netic":[65],"information,":[66],"which":[67],"improves":[69],"robustness":[70],"of":[71,141,144],"document":[73,85,91,101],"ASR":[76],"errors.":[77],"Evaluations":[78],"are":[79],"conducted":[80],"on":[81,112,119,127],"the":[82,107,113,120,145],"English":[83,121],"Wiki-727K":[84],"seg-mentation":[86],"benchmark,":[87],"Chinese":[89,99,128],"Wikipedia-based":[90],"dataset":[93],"we":[94],"created,":[95],"in-house":[98],"dataset.":[102],"Our":[103],"proposed":[104],"outperforms":[106],"state-of-the-art":[108],"(SOTA)":[109],"based":[111],"same":[114],"BERT-Base,":[115],"increasing":[116],"F1":[118],"benchmark":[122],"4.2":[124],"points":[125],"datasets":[129],"4.3-10.1":[131],"points,":[132],"while":[133],"inference":[135,142],"time":[136,143],"less":[138],"than":[139],"1/6":[140],"current":[146],"SOTA.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}