{"id":"https://openalex.org/W7148364812","doi":"https://doi.org/10.1109/asru65441.2025.11434598","title":"WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction","display_name":"WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148364812","doi":"https://doi.org/10.1109/asru65441.2025.11434598"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5001934918","display_name":"Jakaria Islam Emon","orcid":"https://orcid.org/0009-0005-8534-3348"},"institutions":[{"id":"https://openalex.org/I4210129202","display_name":"Denka (Japan)","ror":"https://ror.org/03jaff633","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210129202"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jakaria Islam Emon","raw_affiliation_strings":["Hokkaido Denshikiki Co., Ltd.,Sapporo,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido Denshikiki Co., Ltd.,Sapporo,Japan","institution_ids":["https://openalex.org/I4210129202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132788571","display_name":"Md. Abu Salek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129202","display_name":"Denka (Japan)","ror":"https://ror.org/03jaff633","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210129202"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Md. Abu Salek","raw_affiliation_strings":["Hokkaido Denshikiki Co., Ltd.,Sapporo,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido Denshikiki Co., Ltd.,Sapporo,Japan","institution_ids":["https://openalex.org/I4210129202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120310057","display_name":"Kazi Tamanna Alam","orcid":null},"institutions":[{"id":"https://openalex.org/I3131980151","display_name":"University of Barishal","ror":"https://ror.org/03r0k4b69","country_code":"BD","type":"education","lineage":["https://openalex.org/I3131980151"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Kazi Tamanna Alam","raw_affiliation_strings":["Barisal Information Technology College,Department of Computer Science and Engineering,Barisal,Bangladesh"],"affiliations":[{"raw_affiliation_string":"Barisal Information Technology College,Department of Computer Science and Engineering,Barisal,Bangladesh","institution_ids":["https://openalex.org/I3131980151"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001934918"],"corresponding_institution_ids":["https://openalex.org/I4210129202"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75231339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7208999991416931,"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/T11309","display_name":"Music and Audio Processing","score":0.7208999991416931,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.05810000002384186,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.02319999970495701,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5705000162124634},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5273000001907349},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4916999936103821},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4828999936580658},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.44429999589920044},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3813000023365021},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516000270843506},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5273000001907349},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47049999237060547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6546590328216553,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2972394484","https://openalex.org/W3154961510","https://openalex.org/W4372260310","https://openalex.org/W4385570154","https://openalex.org/W4385571424","https://openalex.org/W4385822828","https://openalex.org/W4392903114","https://openalex.org/W4401023668","https://openalex.org/W4402112395","https://openalex.org/W4402671601","https://openalex.org/W4408353668","https://openalex.org/W4408354411","https://openalex.org/W4412886823","https://openalex.org/W4415433234","https://openalex.org/W4415538351","https://openalex.org/W7133229781"],"related_works":[],"abstract_inverted_index":{"Mean":[0],"Opinion":[1],"Score":[2],"prediction":[3,61],"for":[4,40,50,53,105,109],"text-to-music":[5],"systems":[6],"requires":[7],"evaluating":[8],"both":[9],"overall":[10],"musical":[11],"quality":[12],"and":[13,30,44,78,107],"textprompt":[14],"alignment.":[15],"This":[16],"paper":[17],"introduces":[18],"WhisQ,":[19],"a":[20],"multimodal":[21],"architecture":[22],"that":[23],"tackles":[24],"this":[25],"dual-assessment":[26],"using":[27],"sequencelevel":[28],"co-attention":[29,75],"optimal":[31,81,114],"transport":[32,82,115],"regularization.":[33],"WhisQ":[34,96],"uses":[35,72],"the":[36,88,93,118],"Whisper":[37],"pretrained":[38],"model":[39],"temporal":[41],"audio":[42,68,77],"encoding":[43],"Qwen-3":[45],"(0.6B":[46],"Small":[47],"Language":[48],"Model)":[49],"text":[51],"encoding,":[52],"fine-grained":[54],"cross-modal":[55],"modeling.":[56],"The":[57],"system":[58],"features":[59],"two":[60],"pathways:":[62],"OMQ":[63,106],"is":[64],"predicted":[65],"from":[66],"pooled":[67],"embeddings,":[69],"while":[70],"TA":[71],"bidirectional":[73],"sequence":[74],"between":[76],"text.":[79],"Sinkhorn":[80],"loss":[83],"reinforces":[84],"semantic":[85],"alignment":[86],"in":[87,102],"shared":[89],"embedding":[90],"space.":[91],"On":[92],"MusicEval":[94],"dataset,":[95],"shows":[97],"strong":[98],"performance:":[99],"7%":[100],"improvement":[101],"Spearman":[103],"correlation":[104],"14%":[108],"TA.":[110],"Ablation":[111],"studies":[112],"highlight":[113],"regularization":[116],"as":[117],"key":[119],"driver":[120],"of":[121],"performance":[122],"gains.":[123]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}