{"id":"https://openalex.org/W4372260122","doi":"https://doi.org/10.1109/icassp49357.2023.10095260","title":"Speech Emotion Recognition Based on Low-Level Auto-Extracted Time-Frequency Features","display_name":"Speech Emotion Recognition Based on Low-Level Auto-Extracted Time-Frequency Features","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260122","doi":"https://doi.org/10.1109/icassp49357.2023.10095260"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100349835","display_name":"Ke Liu","orcid":"https://orcid.org/0000-0001-8151-4326"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Liu","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052197725","display_name":"Jingzhao Hu","orcid":"https://orcid.org/0000-0001-9103-8618"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingzhao Hu","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002937692","display_name":"Jun Feng","orcid":"https://orcid.org/0000-0001-9917-1819"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Feng","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100349835"],"corresponding_institution_ids":["https://openalex.org/I37802460"],"apc_list":null,"apc_paid":null,"fwci":0.8694,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73016061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T11309","display_name":"Music and Audio Processing","score":0.9848999977111816,"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/discriminative-model","display_name":"Discriminative model","score":0.8257570266723633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7895640134811401},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6959724426269531},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6518833041191101},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.618741512298584},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5836001634597778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5736599564552307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5581122636795044},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.530596137046814},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5195598602294922},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5042761564254761},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49166184663772583},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08945497870445251},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08487585186958313}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8257570266723633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895640134811401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6959724426269531},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6518833041191101},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.618741512298584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5836001634597778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5736599564552307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5581122636795044},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.530596137046814},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5195598602294922},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5042761564254761},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49166184663772583},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08945497870445251},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08487585186958313},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1542637018","https://openalex.org/W2087750470","https://openalex.org/W2146334809","https://openalex.org/W2164084182","https://openalex.org/W2250521169","https://openalex.org/W2250545560","https://openalex.org/W2252215182","https://openalex.org/W2408520939","https://openalex.org/W2625297138","https://openalex.org/W2747664154","https://openalex.org/W2752782242","https://openalex.org/W2803193013","https://openalex.org/W2889374687","https://openalex.org/W2936113082","https://openalex.org/W2953249574","https://openalex.org/W2962770129","https://openalex.org/W3015240477","https://openalex.org/W3015267357","https://openalex.org/W3015884429","https://openalex.org/W3015969913","https://openalex.org/W3162589478","https://openalex.org/W3163157357","https://openalex.org/W3197977579","https://openalex.org/W4226382702","https://openalex.org/W4385245566","https://openalex.org/W6638444622","https://openalex.org/W6691723933","https://openalex.org/W6739901393","https://openalex.org/W6764726619","https://openalex.org/W6811246235"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W2180954594","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W2735297260","https://openalex.org/W1820289435","https://openalex.org/W1927135183","https://openalex.org/W1596300871","https://openalex.org/W2890436937","https://openalex.org/W3090190000"],"abstract_inverted_index":{"Deep-learning":[0],"based":[1,44],"methods":[2],"that":[3,23,124],"aim":[4],"to":[5,62,84],"extract":[6,85],"effective":[7],"high-level":[8],"features":[9,22,87],"have":[10,28],"steadily":[11],"improved":[12],"the":[13,16,46,57,67,74,79,89,96,104,111,117,125],"performance":[14],"on":[15,45,110],"speech":[17,97],"emotion":[18,98],"recognition.":[19],"However,":[20],"low-level":[21,40,69,120],"contain":[24],"important":[25],"emotion-related":[26],"information":[27],"not":[29],"gained":[30],"much":[31],"attention.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"propose":[37],"a":[38],"novel":[39],"feature":[41,70],"extraction":[42],"method":[43,127],"Time-Frequency":[47,52],"Attention":[48],"(TFA)":[49],"module":[50,59,81],"and":[51,91,113,122],"Weighting":[53],"(TFW)":[54],"module.":[55],"First,":[56],"TFA":[58],"is":[60,82,101],"designed":[61],"learn":[63],"notable":[64],"regions":[65],"in":[66],"detail-rich":[68],"maps":[71],"produced":[72],"by":[73,103],"scale-specific":[75],"convolutional":[76],"layers.":[77],"Then,":[78],"TFW":[80],"proposed":[83,126],"discriminative":[86],"from":[88],"time":[90],"frequency":[92],"dimensions":[93],"respectively.":[94],"Finally,":[95],"recognition":[99],"task":[100],"completed":[102],"subsequent":[105],"multi-branch":[106],"network.":[107],"Experimental":[108],"results":[109],"IEMOCAP":[112],"RAVDESS":[114],"datasets":[115],"demonstrate":[116],"importance":[118],"of":[119],"features,":[121],"show":[123],"outperforms":[128],"other":[129],"state-of-the-art":[130],"approaches.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}