{"id":"https://openalex.org/W2016000176","doi":"https://doi.org/10.1109/iscslp.2012.6423544","title":"Acoustic modeling for native and non-native Mandarin speech recognition","display_name":"Acoustic modeling for native and non-native Mandarin speech recognition","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2016000176","doi":"https://doi.org/10.1109/iscslp.2012.6423544","mag":"2016000176"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423544","doi":"https://doi.org/10.1109/iscslp.2012.6423544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423544","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},"volume":null,"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/A5101964958","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-7163-1892","observed_orcids":["https://orcid.org/0000-0002-7163-1892"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Knowledge Technologies, Pearson, Menlo Park, CA, USA","Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technologies, Pearson, Menlo Park, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112149353","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0003-1289-2758","observed_orcids":["https://orcid.org/0000-0003-1289-2758","https://orcid.org/0000-0001-6966-0531"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["Knowledge Technologies, Pearson, Menlo Park, CA, USA","Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technologies, Pearson, Menlo Park, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2453,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44822533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"325","last_page":"329"},"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-speech-recognition","display_name":"Mandarin speech recognition","score":0.972000002861023},{"id":"https://openalex.org/keywords/non-native-speech","display_name":"non-native speech","score":0.7929999828338623},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.9610000252723694},{"id":"https://openalex.org/keywords/discriminative-training","display_name":"discriminative training","score":0.9929999709129333}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7840362787246704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610951662063599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7078372240066528},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7075059413909912},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6294185519218445},{"id":"https://openalex.org/C2992135444","wikidata":"https://www.wikidata.org/wiki/Q4232928","display_name":"Native american","level":2,"score":0.5134347677230835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4738631248474121},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.451331228017807},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45043352246284485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4384573698043823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37323421239852905},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32156074047088623},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.084227055311203},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2549261","wikidata":"https://www.wikidata.org/wiki/Q43455","display_name":"Ethnology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423544","doi":"https://doi.org/10.1109/iscslp.2012.6423544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423544","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W21249823","https://openalex.org/W73750416","https://openalex.org/W1877570817","https://openalex.org/W2052086036","https://openalex.org/W2146871184","https://openalex.org/W2150907703","https://openalex.org/W2165357419","https://openalex.org/W2405229007","https://openalex.org/W3029593813","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1971734011","https://openalex.org/W1539047115","https://openalex.org/W2378475080","https://openalex.org/W2141731574","https://openalex.org/W1991538182","https://openalex.org/W2079263161","https://openalex.org/W5524598","https://openalex.org/W100022181","https://openalex.org/W2169883442","https://openalex.org/W2377792334"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"first":[4],"described":[5],"the":[6,60],"automatic":[7],"Spoken":[8],"Chinese":[9],"Test":[10],"(SCT).":[11],"With":[12],"a":[13,92],"large":[14],"amount":[15],"of":[16],"native":[17,36,47,66,107],"and":[18,48,59,84,108],"non-native":[19,40,49,74,81,109],"data":[20,50,67,82],"collected":[21],"for":[22,27,105],"SCT,":[23],"different":[24],"training":[25,96],"strategies":[26],"acoustic":[28,53,61],"modeling":[29],"were":[30,33],"investigated.":[31],"Evaluations":[32],"performed":[34],"on":[35,65],"as":[37,39],"well":[38],"datasets.":[41],"We":[42,76],"discovered":[43],"that":[44,86],"directly":[45],"combining":[46],"to":[51,73,79,99],"train":[52],"models":[54],"did":[55],"not":[56],"work":[57],"well,":[58],"model":[62],"trained":[63],"only":[64],"achieved":[68],"better":[69],"performance":[70],"when":[71],"applying":[72],"speech.":[75,111],"investigated":[77],"how":[78],"use":[80],"effectively,":[83],"found":[85,98],"Phonetic":[87],"Decision":[88],"Tree":[89],"(PDT)":[90],"had":[91],"great":[93],"impact.":[94],"Discriminative":[95],"was":[97],"improve":[100],"speech":[101],"recognition":[102],"accuracy":[103],"effectively":[104],"both":[106],"Mandarin":[110]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}