{"id":"https://openalex.org/W4408354943","doi":"https://doi.org/10.1109/icassp49660.2025.10890522","title":"LLaQo: Towards a Query-Based Coach in Expressive Music Performance Assessment","display_name":"LLaQo: Towards a Query-Based Coach in Expressive Music Performance Assessment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354943","doi":"https://doi.org/10.1109/icassp49660.2025.10890522"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5100823846","display_name":"Huan Zhang","orcid":"https://orcid.org/0000-0001-6987-7554"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huan Zhang","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071270743","display_name":"Vincent K.M. Cheung","orcid":"https://orcid.org/0000-0002-0349-4398"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vincent K.M. Cheung","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053651123","display_name":"Hayato Nishioka","orcid":"https://orcid.org/0000-0001-8323-8927"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Nishioka","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053518541","display_name":"Shinichi Furuya","orcid":"https://orcid.org/0000-0003-1387-6645"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichi Furuya","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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":0.9907000064849854,"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/T11425","display_name":"Diverse Music Education Insights","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9763000011444092,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826220989227295},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5683086514472961},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4102728068828583},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34545886516571045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32784587144851685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826220989227295},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5683086514472961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4102728068828583},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34545886516571045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32784587144851685}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2506483933","https://openalex.org/W2735636374","https://openalex.org/W2964051853","https://openalex.org/W3027056244","https://openalex.org/W3047479554","https://openalex.org/W3120724136","https://openalex.org/W3131432709","https://openalex.org/W4372266552","https://openalex.org/W4381516870","https://openalex.org/W4386989254","https://openalex.org/W4388118220","https://openalex.org/W4391021627","https://openalex.org/W4392909390","https://openalex.org/W4402670458","https://openalex.org/W4406794295","https://openalex.org/W6745878906","https://openalex.org/W6764787368","https://openalex.org/W6781149973","https://openalex.org/W6798064515","https://openalex.org/W6799623690","https://openalex.org/W6804049149","https://openalex.org/W6847094994","https://openalex.org/W6847363464","https://openalex.org/W6852818750","https://openalex.org/W6852874933","https://openalex.org/W6853249747","https://openalex.org/W6855932524","https://openalex.org/W6856168926","https://openalex.org/W6857054612","https://openalex.org/W6857577164","https://openalex.org/W6861548716","https://openalex.org/W6870886194","https://openalex.org/W6892507526","https://openalex.org/W6893090372","https://openalex.org/W6911302404"],"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/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Research":[0],"in":[1,125,133,154],"music":[2,66,80],"understanding":[3,105],"has":[4],"extensively":[5],"explored":[6],"composition-level":[7],"attributes":[8],"such":[9,31],"as":[10,32,100,102,107,130,132],"key,":[11],"genre,":[12],"and":[13,35,76,109,115,137],"instrumentation":[14],"through":[15],"advanced":[16],"representations,":[17],"leading":[18],"to":[19,48,73,98,150,169,173],"cross-modal":[20],"applications":[21],"using":[22,44,158],"large":[23,45],"language":[24,46,71],"models.":[25],"However,":[26],"aspects":[27],"of":[28,43,79,92],"musical":[29,174],"performance":[30,93,104,110,128,175],"stylistic":[33],"expression":[34],"technique":[36],"remain":[37],"underexplored,":[38],"along":[39],"with":[40,52],"the":[41],"potential":[42],"models":[47,153],"enhance":[49],"educational":[50],"outcomes":[51],"customized":[53],"feedback.":[54],"To":[55],"bridge":[56],"this":[57],"gap,":[58],"we":[59],"introduce":[60,84],"LLaQo,":[61],"a":[62,90,155],"Large":[63],"Language":[64],"Query-based":[65],"coach":[67],"that":[68,88],"leverages":[69],"audio":[70,177],"modeling":[72],"provide":[74,166],"detailed":[75],"formative":[77],"assessments":[78],"performances.":[81],"We":[82],"also":[83],"instruction-tuned":[85],"query-response":[86],"datasets":[87],"cover":[89],"variety":[91],"dimensions":[94],"from":[95,142,176],"pitch":[96],"accuracy":[97],"articulation,":[99],"well":[101,131],"contextual":[103],"(such":[106],"difficulty":[108,136],"techniques).":[111],"Utilizing":[112],"AudioMAE":[113],"encoder":[114],"Vicuna-7b":[116],"LLM":[117],"backend,":[118],"our":[119],"model":[120,163],"achieved":[121],"state-of-the-art":[122],"(SOTA)":[123],"results":[124],"predicting":[126],"teachers\u2019":[127],"ratings,":[129],"identifying":[134],"piece":[135],"playing":[138],"techniques.":[139],"Textual":[140],"responses":[141],"LLaQo":[143],"was":[144],"moreover":[145],"rated":[146],"significantly":[147],"higher":[148],"compared":[149],"other":[151],"baseline":[152],"user":[156],"study":[157],"audio-text":[159],"matching.":[160],"Our":[161],"proposed":[162],"can":[164],"thus":[165],"informative":[167],"answers":[168],"open-ended":[170],"questions":[171],"related":[172],"data.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}