{"id":"https://openalex.org/W4221161909","doi":"https://doi.org/10.1109/icassp43922.2022.9747637","title":"Sentiment-Aware Automatic Speech Recognition Pre-Training for Enhanced Speech Emotion Recognition","display_name":"Sentiment-Aware Automatic Speech Recognition Pre-Training for Enhanced Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221161909","doi":"https://doi.org/10.1109/icassp43922.2022.9747637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747637","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":"article","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/A5080342868","display_name":"Ayoub Ghriss","orcid":null},"institutions":[{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ayoub Ghriss","raw_affiliation_strings":["University of Colorado,Boulder","University of Colorado, Boulder"],"affiliations":[{"raw_affiliation_string":"University of Colorado,Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]},{"raw_affiliation_string":"University of Colorado, Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067325797","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0002-5866-6492"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Yang","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091009689","display_name":"Viktor Rozgi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Rozgic","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I4210106430","display_name":"Ellipsis","ror":"https://ror.org/01pmtzj45","country_code":"US","type":"other","lineage":["https://openalex.org/I4210106430"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["Ellipsis Health"],"affiliations":[{"raw_affiliation_string":"Ellipsis Health","institution_ids":["https://openalex.org/I4210106430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100713589","display_name":"Chao Wang","orcid":"https://orcid.org/0009-0001-7929-1204"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080342868"],"corresponding_institution_ids":["https://openalex.org/I188538660","https://openalex.org/I2802236040"],"apc_list":null,"apc_paid":null,"fwci":2.4944,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91007905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7347","last_page":"7351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7934228181838989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7802870273590088},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7160792350769043},{"id":"https://openalex.org/keywords/concordance-correlation-coefficient","display_name":"Concordance correlation coefficient","score":0.6105840802192688},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5653331875801086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.53116375207901},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5097958445549011},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.5081887245178223},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4920637011528015},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46706610918045044},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40698856115341187},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3255949020385742},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32475197315216064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934228181838989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7802870273590088},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7160792350769043},{"id":"https://openalex.org/C2781059462","wikidata":"https://www.wikidata.org/wiki/Q5158906","display_name":"Concordance correlation coefficient","level":2,"score":0.6105840802192688},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5653331875801086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53116375207901},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5097958445549011},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.5081887245178223},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4920637011528015},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46706610918045044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40698856115341187},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3255949020385742},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32475197315216064},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747637","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":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1966797434","https://openalex.org/W2127141656","https://openalex.org/W2134891270","https://openalex.org/W2146334809","https://openalex.org/W2152137767","https://openalex.org/W2511566646","https://openalex.org/W2742542661","https://openalex.org/W2752234108","https://openalex.org/W2774085128","https://openalex.org/W2842511635","https://openalex.org/W2936774411","https://openalex.org/W2962770129","https://openalex.org/W2963001203","https://openalex.org/W2995545690","https://openalex.org/W3004449907","https://openalex.org/W3015707499","https://openalex.org/W3016011332","https://openalex.org/W3096147072","https://openalex.org/W3099215402","https://openalex.org/W3162811262","https://openalex.org/W3197236059","https://openalex.org/W4297808394","https://openalex.org/W6629717138","https://openalex.org/W6746468907"],"related_works":["https://openalex.org/W4286692883","https://openalex.org/W2992378684","https://openalex.org/W2122233706","https://openalex.org/W4221161909","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W2186896963","https://openalex.org/W4372346152","https://openalex.org/W4361192867","https://openalex.org/W2131711534"],"abstract_inverted_index":{"We":[0,12,35,61],"propose":[1],"a":[2],"novel":[3],"multi-task":[4],"pre-training":[5],"method":[6],"for":[7,38,81],"Speech":[8,19],"Emotion":[9],"Recognition":[10,20],"(SER).":[11],"pre-train":[13],"SER":[14],"model":[15,31,44],"simultaneously":[16],"on":[17,46,56,66],"Automatic":[18],"(ASR)":[21],"and":[22],"sentiment":[23,40],"classification":[24,41],"tasks":[25],"to":[26],"make":[27],"the":[28,39,53,63,72],"acoustic":[29,54],"ASR":[30,55],"more":[32],"\"emotion":[33],"aware\".":[34],"generate":[36],"targets":[37],"using":[42],"text-to-sentiment":[43],"trained":[45],"publicly":[47],"available":[48],"data.":[49,60],"Finally,":[50],"we":[51,70],"fine-tune":[52],"emotion":[57],"annotated":[58],"speech":[59],"evaluated":[62],"proposed":[64],"approach":[65],"MSP-Podcast":[67],"dataset,":[68],"where":[69],"achieved":[71],"best":[73],"reported":[74],"concordance":[75],"correlation":[76],"coefficient":[77],"(CCC)":[78],"of":[79],"0.41":[80],"valence":[82],"prediction.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}