{"id":"https://openalex.org/W4385823091","doi":"https://doi.org/10.21437/interspeech.2023-587","title":"Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring","display_name":"Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823091","doi":"https://doi.org/10.21437/interspeech.2023-587"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-587","doi":"https://doi.org/10.21437/interspeech.2023-587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-587","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"INTERSPEECH 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.11438","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074965408","display_name":"Kaiqi Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiqi Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050588994","display_name":"Shaojun Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006589840","display_name":"Shuju Shi","orcid":"https://orcid.org/0000-0002-8349-1145","observed_orcids":["https://orcid.org/0000-0002-8349-1145"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuju Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100959470","display_name":"Xiaohai Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohai Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317994","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7015-7335","observed_orcids":["https://orcid.org/0000-0001-7015-7335","https://orcid.org/0009-0002-8566-6073","https://orcid.org/0000-0003-3335-3200"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.476,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61642994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"949","last_page":"953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9096999764442444,"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":0.9096999764442444,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.055799998342990875,"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/T12031","display_name":"Speech and dialogue systems","score":0.004800000227987766,"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/self-supervised-learning","display_name":"self-supervised learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/phonetic-features","display_name":"phonetic features","score":0.7450000047683716},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.9350000023841858},{"id":"https://openalex.org/keywords/second-language-speech","display_name":"second language speech","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8459136486053467},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.8310074210166931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546685695648193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5310751795768738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094264149665833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46203282475471497},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2899758815765381},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-587","doi":"https://doi.org/10.21437/interspeech.2023-587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-587","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.11438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11438","pdf_url":"https://arxiv.org/pdf/2305.11438","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.11438","doi":"https://doi.org/10.48550/arxiv.2305.11438","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.11438","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.11438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11438","pdf_url":"https://arxiv.org/pdf/2305.11438","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823091.pdf","grobid_xml":"https://content.openalex.org/works/W4385823091.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4372259940","https://openalex.org/W4417053948","https://openalex.org/W7108465977","https://openalex.org/W2262459280","https://openalex.org/W3011582891","https://openalex.org/W4297841403","https://openalex.org/W4417150076","https://openalex.org/W4313394195","https://openalex.org/W2141001701","https://openalex.org/W4408200920"],"abstract_inverted_index":{"Speech":[0],"fluency/disfluency":[1],"can":[2],"be":[3],"evaluated":[4],"by":[5,37,77],"analyzing":[6],"a":[7,50,73,85],"range":[8],"of":[9,31,41,88,128,145],"phonetic":[10,59,146],"and":[11,60,80,91,113,147],"prosodic":[12],"features.":[13],"Deep":[14],"neural":[15],"networks":[16],"are":[17],"commonly":[18],"trained":[19],"to":[20,140],"map":[21],"fluency-related":[22],"features":[23],"into":[24,57],"the":[25,29,38,70,97,123,143,151],"human":[26],"scores.":[27],"However,":[28],"effectiveness":[30],"deep":[32],"learning-based":[33],"models":[34],"is":[35],"constrained":[36],"limited":[39],"amount":[40,87],"labeled":[42],"training":[43],"samples.":[44],"To":[45],"address":[46],"this,":[47],"we":[48,67,134],"introduce":[49],"self-supervised":[51],"learning":[52],"(SSL)":[53],"approach":[54],"that":[55,118],"takes":[56],"account":[58],"prosody":[61,148],"awareness":[62],"for":[63],"fluency":[64],"scoring.":[65],"Specifically,":[66],"first":[68],"pre-train":[69],"model":[71,99],"using":[72,100],"reconstruction":[74],"loss":[75],"function,":[76],"masking":[78],"phones":[79],"their":[81],"durations":[82],"jointly":[83],"on":[84,108],"large":[86],"unlabeled":[89],"speech":[90],"text":[92],"prompts.":[93],"We":[94],"then":[95],"fine-tune":[96],"pre-trained":[98],"human-annotated":[101],"scoring":[102],"data.":[103],"Our":[104],"experimental":[105],"results,":[106],"conducted":[107],"datasets":[109],"such":[110],"as":[111],"Speechocean762":[112],"our":[114,119],"non-native":[115],"datasets,":[116],"show":[117],"proposed":[120],"method":[121],"outperforms":[122],"baseline":[124],"systems":[125],"in":[126],"terms":[127],"Pearson":[129],"correlation":[130],"coefficients":[131],"(PCC).":[132],"Moreover,":[133],"also":[135],"conduct":[136],"an":[137],"ablation":[138],"study":[139],"better":[141],"understand":[142],"contribution":[144],"factors":[149],"during":[150],"pre-training":[152],"stage.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-08-15T00:00:00"}