{"id":"https://openalex.org/W2999528291","doi":"https://doi.org/10.1145/3338533.3366579","title":"A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading","display_name":"A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading","publication_year":2019,"publication_date":"2019-12-15","ids":{"openalex":"https://openalex.org/W2999528291","doi":"https://doi.org/10.1145/3338533.3366579","mag":"2999528291"},"language":"en","primary_location":{"id":"doi:10.1145/3338533.3366579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3338533.3366579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Asia","raw_type":"proceedings-article"},"type":"preprint","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/A5113892134","display_name":"Ya Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ya Zhao","raw_affiliation_strings":["Zhejiang Provincial Key Laboratory of Service Robots Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Provincial Key Laboratory of Service Robots Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888899","display_name":"Rui Xu","orcid":"https://orcid.org/0000-0002-5549-236X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["Zhejiang Provincial Key Laboratory of Service Robots Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Provincial Key Laboratory of Service Robots Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Zhejiang Provincial Key Laboratory of Service Robots Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Provincial Key Laboratory of Service Robots Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113892134"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.8606,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.94634265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9672999978065491,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8942726254463196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408461570739746},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7236963510513306},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6032162308692932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5987716317176819},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5275639891624451},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4576910436153412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45424848794937134},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.4533481299877167},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.4514429569244385},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.41927963495254517},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4022022485733032}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8942726254463196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408461570739746},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7236963510513306},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6032162308692932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5987716317176819},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5275639891624451},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4576910436153412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45424848794937134},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.4533481299877167},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.4514429569244385},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.41927963495254517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4022022485733032},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3338533.3366579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3338533.3366579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8799999952316284,"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":14,"referenced_works":["https://openalex.org/W50577135","https://openalex.org/W648786980","https://openalex.org/W1975370719","https://openalex.org/W2115252128","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2404704342","https://openalex.org/W2551572271","https://openalex.org/W2952746495","https://openalex.org/W2961383076","https://openalex.org/W2962778134","https://openalex.org/W2963173190","https://openalex.org/W2963850025","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2393887907","https://openalex.org/W2347443630","https://openalex.org/W2388826840","https://openalex.org/W2481138693","https://openalex.org/W2379831327","https://openalex.org/W2386691339","https://openalex.org/W2163874654","https://openalex.org/W156219719","https://openalex.org/W2365805939","https://openalex.org/W2287147624"],"abstract_inverted_index":{"Lip":[0,115],"reading":[1,17,57,146],"aims":[2],"at":[3,25],"decoding":[4],"texts":[5],"from":[6,127],"the":[7,52,55,137,141,150],"movement":[8],"of":[9,122,143,152,155],"a":[10,36,64,109],"speaker's":[11],"mouth.":[12],"In":[13,59,104],"recent":[14],"years,":[15],"lip":[16,56,72,145,160],"methods":[18],"have":[19],"made":[20],"great":[21],"progress":[22],"for":[23,54,68,157],"English,":[24,31],"both":[26],"word-level":[27],"and":[28,39,88,91,101,119],"sentence-level.":[29],"Unlike":[30],"however,":[32],"Chinese":[33,69,158],"Mandarin":[34,70,114,159],"is":[35,117],"tone-based":[37],"language":[38],"relies":[40],"on":[41,85,134],"pitches":[42],"to":[43,94,106],"distinguish":[44],"lexical":[45],"or":[46],"grammatical":[47],"meaning,":[48],"which":[49,74,148],"significantly":[50],"increases":[51],"ambiguity":[53],"task.":[58],"this":[60],"paper,":[61],"we":[62],"propose":[63],"Cascade":[65],"Sequence-to-Sequence":[66],"Model":[67],"(CSSMCM)":[71],"reading,":[73],"explicitly":[75],"models":[76],"tones":[77,156],"when":[78],"predicting":[79],"sentence.":[80],"Tones":[81],"are":[82,92],"modeled":[83],"based":[84],"visual":[86,99],"information":[87,100],"syntactic":[89,102],"structure,":[90],"used":[93],"predict":[95],"sentence":[96],"along":[97],"with":[98],"structure.":[103],"order":[105],"evaluate":[107],"CSSMCM,":[108],"dataset":[110],"called":[111],"CMLR":[112,135],"(Chinese":[113],"Reading)":[116],"collected":[118],"released,":[120],"consisting":[121],"over":[123],"100,000":[124],"natural":[125],"sentences":[126],"China":[128],"Network":[129],"Television":[130],"website.":[131],"When":[132],"trained":[133],"dataset,":[136],"proposed":[138],"CSSMCM":[139],"surpasses":[140],"performance":[142],"state-of-the-art":[144],"frameworks,":[147],"confirms":[149],"effectiveness":[151],"explicit":[153],"modeling":[154],"reading.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}