{"id":"https://openalex.org/W4388820721","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317449","title":"Contribution of modulation spectral features for cross-lingual speech emotion recognition under noisy reverberant conditions","display_name":"Contribution of modulation spectral features for cross-lingual speech emotion recognition under noisy reverberant conditions","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820721","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317449"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317449","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5112906842","display_name":"Taiyang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taiyang Guo","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061418266","display_name":"Sixia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sixia Li","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019041248","display_name":"Shunsuke Kidani","orcid":"https://orcid.org/0000-0001-6491-9540"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shunsuke Kidani","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080920610","display_name":"Shogo Okada","orcid":"https://orcid.org/0000-0002-9260-0403"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Okada","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Japan,923-1292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.3521,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59734513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"33","issue":null,"first_page":"2221","last_page":"2227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","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/speech-recognition","display_name":"Speech recognition","score":0.5498526096343994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43473172187805176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3910375237464905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3752245306968689},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3445737361907959}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5498526096343994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43473172187805176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3910375237464905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3752245306968689},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3445737361907959}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317449","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2493814986","display_name":"Autonomous improvement of spoken ialogue systems through incremental knowledge acquisition","funder_award_id":"22H00536","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3240679960","display_name":"Auditory Enrichment based on perception of amplitude modulation: Study on speech signal processing for Cochlear Implant","funder_award_id":"23K21679","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3635912132","display_name":"VOICE 2.0: towards augmentation of enriched speech communication","funder_award_id":"20KK0233","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1974843131","https://openalex.org/W2006473853","https://openalex.org/W2064641533","https://openalex.org/W2095161034","https://openalex.org/W2112854909","https://openalex.org/W2123119128","https://openalex.org/W2141853407","https://openalex.org/W2146334809","https://openalex.org/W2147727981","https://openalex.org/W2159408788","https://openalex.org/W2239141610","https://openalex.org/W2395913652","https://openalex.org/W2602034649","https://openalex.org/W2785960144","https://openalex.org/W2810490977","https://openalex.org/W2883496341","https://openalex.org/W2888792135","https://openalex.org/W2899172842","https://openalex.org/W2928112693","https://openalex.org/W2939488497","https://openalex.org/W2963087748","https://openalex.org/W2997327816","https://openalex.org/W3036601975","https://openalex.org/W3120709499","https://openalex.org/W3197642003","https://openalex.org/W3198528147","https://openalex.org/W3216586892","https://openalex.org/W4285235436","https://openalex.org/W4303614142","https://openalex.org/W4312120856","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Handling":[0],"multiple":[1],"languages":[2,44,65,97],"under":[3,66,118],"noisy":[4,27,68,119],"reverberant":[5,28,69,120],"conditions":[6,29,81,94,121],"has":[7],"become":[8],"increasingly":[9],"important":[10],"for":[11,30,61,130],"speech":[12],"emotion":[13],"recognition":[14],"(SER).":[15],"Previous":[16],"studies":[17],"found":[18],"that":[19,74,88,111,124],"modulation":[20],"spectral":[21],"features":[22,60,76,129],"(MSFs)":[23],"are":[24,113,126],"robust":[25,114],"to":[26,115],"SER.":[31],"However,":[32],"they":[33],"mainly":[34],"focused":[35],"on":[36,63,79,92,100,106],"specific":[37],"languages;":[38],"the":[39],"universality":[40],"of":[41,82,95],"MSFs":[42,89,112,125],"among":[43],"is":[45],"still":[46],"unclear.":[47],"To":[48],"address":[49],"this":[50],"issue,":[51],"we":[52],"compared":[53],"MSFs,":[54],"hand-crafted":[55],"features,":[56,58],"Wav2Vec2.0-based":[57],"MSFs+hand-crafted":[59,75],"SER":[62,117],"four":[64],"12":[67],"conditions.":[70],"Intra-lingual":[71],"results":[72,86,109],"showed":[73,87],"performed":[77,90],"best":[78,91],"most":[80,93],"all":[83],"languages.":[84,132],"Inter-lingual":[85],"test":[96],"except":[98],"training":[99],"a":[101],"tonal":[102],"language":[103],"and":[104,122],"testing":[105],"others.":[107],"The":[108],"demonstrate":[110],"multilingual":[116],"suggest":[123],"potentially":[127],"language-independent":[128],"nontonal":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}