{"id":"https://openalex.org/W3196487394","doi":"https://doi.org/10.21437/interspeech.2021-1167","title":"Additive Phoneme-Aware Margin Softmax Loss for Language Recognition","display_name":"Additive Phoneme-Aware Margin Softmax Loss for Language Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196487394","doi":"https://doi.org/10.21437/interspeech.2021-1167","mag":"3196487394"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5100415030","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-9165-6878"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350993","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0001-6112-7898"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["School of Informatics, Xiamen University, China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3276","last_page":"3280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9979000091552734,"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/softmax-function","display_name":"Softmax function","score":0.9932082891464233},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.8546977639198303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6827776432037354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244331002235413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.566275954246521},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48979759216308594},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47521382570266724},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43573856353759766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3400319814682007},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24662691354751587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18146485090255737}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9932082891464233},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8546977639198303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827776432037354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244331002235413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.566275954246521},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48979759216308594},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47521382570266724},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43573856353759766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3400319814682007},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24662691354751587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18146485090255737},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2299475589","display_name":null,"funder_award_id":"62001405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3698338998","display_name":null,"funder_award_id":"61876160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2027286570","https://openalex.org/W2056119007","https://openalex.org/W2078169166","https://openalex.org/W2150769028","https://openalex.org/W2183016404","https://openalex.org/W2284628133","https://openalex.org/W2340176088","https://openalex.org/W2408021097","https://openalex.org/W2500968368","https://openalex.org/W2612434969","https://openalex.org/W2747238065","https://openalex.org/W2807627734","https://openalex.org/W2888897023","https://openalex.org/W2889385246","https://openalex.org/W2899771611","https://openalex.org/W2940070181","https://openalex.org/W2963063081","https://openalex.org/W2963307329","https://openalex.org/W2963466847","https://openalex.org/W2964010794","https://openalex.org/W2964247977","https://openalex.org/W2969985801","https://openalex.org/W2972743990","https://openalex.org/W2972961496","https://openalex.org/W2972986505","https://openalex.org/W2973032144","https://openalex.org/W3010814938","https://openalex.org/W3015678397","https://openalex.org/W3103152812","https://openalex.org/W3140102771","https://openalex.org/W3163421828","https://openalex.org/W4234330420","https://openalex.org/W4289465850","https://openalex.org/W4289750118","https://openalex.org/W4361745846"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W2982889384","https://openalex.org/W4226227567","https://openalex.org/W2971218105","https://openalex.org/W4287113729","https://openalex.org/W3173314472","https://openalex.org/W3103152812","https://openalex.org/W1773599773","https://openalex.org/W2268150819"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,77],"additive":[4,22,56,90],"phoneme-aware":[5,91],"margin":[6,23,28,58,65,92,102],"softmax":[7,24,59],"(APM-Softmax)":[8],"loss":[9,79,129,132],"to":[10,109],"train":[11],"the":[12,27,35,49,62,89,101,110,124],"multi-task":[13,85],"learning":[14],"network":[15],"with":[16,83],"phonetic":[17],"information":[18],"for":[19,38,80,96],"language":[20,81,104,135],"recognition.In":[21],"(AM-Softmax)":[25],"loss,":[26,61],"is":[29,44,66,93,106],"set":[30,67],"as":[31,68,71],"a":[32,45,69],"constant":[33],"during":[34],"entire":[36],"training":[37,40,54,98],"all":[39],"samples,":[41],"and":[42,123,130],"that":[43],"suboptimal":[46],"method":[47,126],"since":[48],"recognition":[50,82,105,136],"difficulty":[51],"varies":[52],"in":[53,87,133],"samples.In":[55],"angular":[57,64],"(AAM-Softmax)":[60],"additional":[63],"costant":[70],"well.In":[72],"this":[73],"paper,":[74],"we":[75],"propose":[76],"APM-Softmax":[78],"phoneitc":[84],"learning,":[86],"which":[88],"automatically":[94],"tuned":[95],"different":[97,134],"samples.More":[99],"specifically,":[100],"of":[103,112],"adjusted":[107],"according":[108],"results":[111],"phoneme":[113],"recognition.Experiments":[114],"are":[115],"reported":[116],"on":[117],"Oriental":[118],"Language":[119],"Recognition":[120],"(OLR)":[121],"datasets,":[122],"proposed":[125],"improves":[127],"AM-Softmax":[128],"AAM-Softmax":[131],"testing":[137],"conditions.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}