{"id":"https://openalex.org/W4416799148","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249325","title":"DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction","display_name":"DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799148","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249325"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5042112521","display_name":"Cheng-Yeh Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Cheng-Yeh Yang","raw_affiliation_strings":["National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841009","display_name":"Kui Huang","orcid":"https://orcid.org/0009-0005-5411-581X"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Tang Huang","raw_affiliation_strings":["National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053163537","display_name":"Chien-Chun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Chun Wang","raw_affiliation_strings":["National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["United Link Co., Ltd.,Taiwan"],"affiliations":[{"raw_affiliation_string":"United Link Co., Ltd.,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053222355","display_name":"Berlin Chen","orcid":"https://orcid.org/0000-0003-0693-8932"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,* Dept. of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042112521"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47971448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2038","last_page":"2043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5554999709129333,"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":0.5554999709129333,"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":0.21469999849796295,"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":0.05570000037550926,"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/pooling","display_name":"Pooling","score":0.9230999946594238},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6287000179290771},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5710999965667725},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.541700005531311},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5202999711036682},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.460099995136261},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.43160000443458557}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9230999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6847000122070312},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6287000179290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215999722480774},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5202999711036682},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3244999945163727},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2919999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2889519245","https://openalex.org/W2951019013","https://openalex.org/W2963216120","https://openalex.org/W2963371159","https://openalex.org/W2963559058","https://openalex.org/W2972369255","https://openalex.org/W2972425344","https://openalex.org/W3011837469","https://openalex.org/W3015197287","https://openalex.org/W3024869864","https://openalex.org/W3095992690","https://openalex.org/W3096084197","https://openalex.org/W3198742213","https://openalex.org/W3202278141","https://openalex.org/W4317538423","https://openalex.org/W4372260310","https://openalex.org/W4385823321","https://openalex.org/W4392903114","https://openalex.org/W4403780831","https://openalex.org/W4408353668","https://openalex.org/W4412945617"],"related_works":[],"abstract_inverted_index":{"A":[0],"pooling":[1,29,165],"mechanism":[2],"is":[3],"essential":[4],"for":[5],"mean":[6],"opinion":[7],"score":[8],"(MOS)":[9],"prediction,":[10],"facilitating":[11],"the":[12,61,99,111,118,162],"transformation":[13],"of":[14,79,117,151],"variable-length":[15],"audio":[16,144],"features":[17],"into":[18],"a":[19,34,40,45,91,137,148],"concise":[20],"fixed-size":[21],"representation":[22],"that":[23],"effectively":[24],"encodes":[25],"speech":[26],"quality.":[27],"Existing":[28],"methods":[30,126],"typically":[31],"operate":[32],"at":[33],"singular":[35],"granularity,":[36],"concentrating":[37],"either":[38],"on":[39],"comprehensive":[41],"global":[42,72],"perspective":[43],"or":[44],"detailed":[46],"frame-level":[47],"analysis,":[48],"which":[49],"may":[50],"overlook":[51],"complementary":[52],"perceptual":[53],"insights.":[54],"To":[55],"address":[56],"this":[57],"limitation,":[58],"we":[59],"introduce":[60],"Dual-Resolution":[62],"Attentive":[63],"Statistics":[64],"Pooling":[65],"(DRASP)":[66],"framework.":[67,120],"DRASP":[68],"integrates":[69],"both":[70,98],"coarse-grained,":[71],"statistical":[73],"summaries":[74],"and":[75,94,103,113,131,140,142],"fine-grained,":[76],"attentive":[77],"analyses":[78],"perceptually":[80],"significant":[81],"segments.":[82],"This":[83],"dual-view":[84],"architecture":[85],"empowers":[86],"our":[87],"model":[88,139],"to":[89],"formulate":[90],"more":[92],"thorough":[93],"robust":[95],"representation,":[96],"capturing":[97],"overarching":[100],"structural":[101],"context":[102],"salient":[104],"local":[105],"details":[106],"concurrently.":[107],"Extensive":[108],"experiments":[109],"validate":[110],"effectiveness":[112],"strong":[114],"generalization":[115],"ability":[116],"proposed":[119],"It":[121],"consistently":[122],"outperforms":[123],"various":[124],"baseline":[125],"across":[127],"diverse":[128],"datasets":[129],"(MusicEval":[130],"AES-Natural),":[132],"MOS":[133],"prediction":[134],"backbones":[135],"(including":[136],"CLAP-based":[138],"AudioBox-Aesthetics),":[141],"different":[143],"generation":[145],"systems,":[146],"achieving":[147],"relative":[149],"improvement":[150],"10.39":[152],"%":[153],"in":[154],"system-level":[155],"Spearman's":[156],"rank":[157],"correlation":[158],"coefficient":[159],"(SRCC)":[160],"over":[161],"widely-used":[163],"average":[164],"approach.":[166]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}