{"id":"https://openalex.org/W2888977743","doi":"https://doi.org/10.21437/interspeech.2018-1087","title":"A Deep Learning Approach to Assessing Non-native Pronunciation of English Using Phone Distances","display_name":"A Deep Learning Approach to Assessing Non-native Pronunciation of English Using Phone Distances","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888977743","doi":"https://doi.org/10.21437/interspeech.2018-1087","mag":"2888977743"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1087","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17863/cam.30281","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046799023","display_name":"Konstantinos G. Kyriakopoulos","orcid":"https://orcid.org/0000-0002-7498-4589"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Konstantinos Kyriakopoulos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Gales","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046799023"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6923,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88255619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1626","last_page":"1630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/phone","display_name":"Phone","score":0.8354635238647461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878177165985107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5962499380111694},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.577520489692688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5319027900695801},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.487571656703949},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.459127277135849},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4476197063922882},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4203948676586151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3389432728290558},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3233930468559265},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08324480056762695}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.8354635238647461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878177165985107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5962499380111694},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.577520489692688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5319027900695801},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.487571656703949},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.459127277135849},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4476197063922882},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4203948676586151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3389432728290558},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3233930468559265},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08324480056762695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-1087","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:1011508","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1011508/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/282918","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/282918","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"doi:10.17863/cam.30281","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.30281","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.17863/cam.30281","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.30281","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1593899244","https://openalex.org/W2020332649","https://openalex.org/W2077155272","https://openalex.org/W2091359957","https://openalex.org/W2139008940","https://openalex.org/W2508865106","https://openalex.org/W2770835169"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W2894446834"],"abstract_inverted_index":{"The":[0,103],"way":[1],"a":[2,9,43,55,97,110],"non-native":[3],"speaker":[4],"pronounces":[5],"the":[6,22,52,67,75,119,123,130,133,137],"phones":[7],"of":[8,15,54,132],"language":[10],"is":[11,106,126,143,157],"an":[12,85],"important":[13],"predictor":[14],"their":[16],"proficiency.":[17],"In":[18],"grading":[19],"spontaneous":[20],"speech,":[21],"pairwise":[23],"distances":[24,50,89],"between":[25,90],"generative":[26],"statistical":[27],"models":[28],"trained":[29],"on":[30,108],"each":[31],"phone":[32,49,76,91,112,151],"have":[33],"been":[34],"shown":[35],"to":[36,47,61,81,100,117,136,150],"be":[37],"powerful":[38],"features.":[39],"This":[40,141],"paper":[41],"presents":[42],"deep":[44],"learning":[45,131],"alternative":[46],"model-based":[48,120],"in":[51],"form":[53],"tunable":[56],"Siamese":[57],"network":[58],"feature":[59],"extractor":[60],"extract":[62],"distance":[63,134],"metrics":[64],"directly":[65],"from":[66],"audio":[68],"frame":[69],"sequence.":[70],"Features":[71],"are":[72,93],"extracted":[73],"at":[74],"instance":[77,152],"level":[78,153],"and":[79,147],"combined":[80],"phone-level":[82],"representations":[83],"using":[84],"attention":[86],"mechanism.":[87],"Pair-wise":[88],"features":[92],"then":[94,122],"projected":[95],"through":[96],"feed-forward":[98],"layer":[99],"predict":[101],"score.":[102],"extraction":[104],"stage":[105],"initialised":[107],"either":[109],"binary":[111],"instance-pair":[113],"classification":[114],"task,":[115],"or":[116],"mimic":[118],"features,":[121],"whole":[124],"system":[125],"fine-tuned":[127],"end-to-end,":[128],"optimising":[129],"metric":[135],"score":[138],"prediction":[139],"task.":[140],"method":[142],"therefore":[144],"more":[145,148],"adaptable":[146],"sensitive":[149],"phenomena.":[154],"Its":[155],"performance":[156],"compared":[158],"against":[159]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}