{"id":"https://openalex.org/W4221162872","doi":"https://doi.org/10.1109/icassp43922.2022.9747095","title":"Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information","display_name":"Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221162872","doi":"https://doi.org/10.1109/icassp43922.2022.9747095"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747095","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5023152132","display_name":"Heqing Zou","orcid":"https://orcid.org/0000-0003-0038-2822"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005255412","display_name":"Yuke Si","orcid":"https://orcid.org/0009-0009-7170-1916"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Si","raw_affiliation_strings":["Tianjin University,China","Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009372982","display_name":"Deepu Rajan","orcid":"https://orcid.org/0000-0001-7788-8368"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deepu Rajan","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":162,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7367","last_page":"7371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7131495475769043},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7124113440513611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6763548254966736}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7131495475769043},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7124113440513611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6763548254966736}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747095","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2032254851","https://openalex.org/W2146334809","https://openalex.org/W2158705122","https://openalex.org/W2191779130","https://openalex.org/W2408520939","https://openalex.org/W2885005742","https://openalex.org/W2889374687","https://openalex.org/W2936113082","https://openalex.org/W2972498864","https://openalex.org/W2973181312","https://openalex.org/W3015906487","https://openalex.org/W3015969913","https://openalex.org/W3036601975","https://openalex.org/W3096723250","https://openalex.org/W3160039712","https://openalex.org/W3160183718","https://openalex.org/W3160222702","https://openalex.org/W3162160536","https://openalex.org/W3162475537","https://openalex.org/W3163091219","https://openalex.org/W3198528147","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/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"aims":[4],"to":[5,9],"help":[6],"the":[7,62,85,93],"machine":[8],"understand":[10],"human\u2019s":[11],"subjective":[12],"emotion":[13,39],"from":[14],"only":[15],"audio":[16,24],"in-formation.":[17],"However,":[18],"extracting":[19],"and":[20,61,70,82,96],"utilizing":[21],"comprehensive":[22],"in-depth":[23],"information":[25,45,66],"is":[26,110],"still":[27],"a":[28,47],"challenging":[29],"task.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"an":[36],"end-to-end":[37],"speech":[38],"recognition":[40],"system":[41],"using":[42],"multi-level":[43,55],"acoustic":[44,56,65],"with":[46,67,102],"newly":[48],"designed":[49],"co-attention":[50,87],"module.":[51],"We":[52],"firstly":[53],"extract":[54],"information,":[57],"including":[58],"MFCC,":[59],"spectrogram,":[60],"embedded":[63],"high-level":[64],"CNN,":[68],"BiL-STM":[69],"wav2vec2,":[71],"respectively.":[72],"Then":[73],"these":[74],"extracted":[75],"features":[76],"are":[77,90],"treated":[78],"as":[79],"multimodal":[80],"inputs":[81],"fused":[83],"by":[84],"pro-posed":[86],"mechanism.":[88],"Experiments":[89],"carried":[91],"on":[92,112],"IEMOCAP":[94],"dataset,":[95],"our":[97],"model":[98],"achieves":[99],"competitive":[100],"performance":[101],"two":[103],"different":[104],"speaker-independent":[105],"cross-validation":[106],"strategies.":[107],"Our":[108],"code":[109],"available":[111],"GitHub.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}