{"id":"https://openalex.org/W3134747183","doi":"https://doi.org/10.1109/iscslp49672.2021.9362050","title":"Syllable-Based Acoustic Modeling With Lattice-Free MMI for Mandarin Speech Recognition","display_name":"Syllable-Based Acoustic Modeling With Lattice-Free MMI for Mandarin Speech Recognition","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3134747183","doi":"https://doi.org/10.1109/iscslp49672.2021.9362050","mag":"3134747183"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100679241","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-4974-6116"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027251228","display_name":"Zhiyun Fan","orcid":"https://orcid.org/0000-0001-9180-7392"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyun Fan","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, P.R.China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101886099","display_name":"Yan Li","orcid":"https://orcid.org/0000-0003-3566-0992"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7587058544158936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7585105895996094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7543842196464539},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6840659976005554},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.610629677772522},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47419315576553345},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44679194688796997},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42664605379104614},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4166911840438843},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4155799150466919},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4136517643928528},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34337013959884644},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17107108235359192}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7587058544158936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585105895996094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7543842196464539},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6840659976005554},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.610629677772522},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47419315576553345},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44679194688796997},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42664605379104614},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4166911840438843},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4155799150466919},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4136517643928528},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34337013959884644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17107108235359192},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W199894982","https://openalex.org/W1524333225","https://openalex.org/W1525636403","https://openalex.org/W1571745681","https://openalex.org/W1578856370","https://openalex.org/W1779452081","https://openalex.org/W1974387177","https://openalex.org/W2096466030","https://openalex.org/W2121464381","https://openalex.org/W2147768505","https://openalex.org/W2158069733","https://openalex.org/W2167200294","https://openalex.org/W2169455968","https://openalex.org/W2293634267","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2729190387","https://openalex.org/W2786031273","https://openalex.org/W2888226713","https://openalex.org/W2888867175","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2962778134","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2963850025","https://openalex.org/W4297797495","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6638005537","https://openalex.org/W6696934422","https://openalex.org/W6739901393","https://openalex.org/W6753776127","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593"],"abstract_inverted_index":{"Most":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"systems":[5],"in":[6,93],"past":[7],"decades":[8],"have":[9],"used":[10],"context-dependent":[11],"(CD)":[12],"phones":[13],"as":[14],"the":[15,76,82,87,107,124,132],"fundamental":[16],"acoustic":[17,50,61,99],"units.":[18],"However,":[19],"these":[20],"phone-based":[21,134],"approaches":[22],"lack":[23],"an":[24],"easy":[25],"and":[26,86,112],"efficient":[27],"way":[28],"for":[29,63],"modeling":[30,95],"long-term":[31,97],"temporal":[32,98],"dependencies.":[33],"Compared":[34],"with":[35,66,141],"phone":[36],"units,":[37,81],"syllables":[38],"span":[39],"a":[40,59],"longer":[41,79],"time,":[42],"typically":[43],"several":[44],"phones,":[45],"thereby":[46],"having":[47],"more":[48],"stable":[49],"realizations.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"aim":[56],"to":[57,105],"train":[58],"syllable-based":[60,110,126],"model":[62,84],"Mandarin":[64],"ASR":[65],"lattice-free":[67],"maximum":[68],"mutual":[69],"information":[70],"(LF-MMI)":[71],"criterion.":[72],"We":[73,101],"expect":[74],"that,":[75],"combination":[77],"of":[78,96,109],"linguistic":[80],"RNN-based":[83],"structure":[85],"sequence-level":[88],"objective":[89],"function,":[90],"can":[91],"result":[92],"better":[94,130],"variations.":[100],"make":[102],"multiple":[103],"modifications":[104],"improve":[106],"performance":[108],"AM":[111,127],"benchmark":[113],"our":[114],"models":[115],"on":[116,137],"two":[117],"large-scale":[118],"databases.":[119],"Experimental":[120],"results":[121],"show":[122],"that":[123],"proposed":[125],"performs":[128],"much":[129],"than":[131],"CD":[133],"baseline,":[135],"especially":[136],"noisy":[138],"test":[139],"sets,":[140],"faster":[142],"decoding":[143],"speed.":[144]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}