{"id":"https://openalex.org/W4200250820","doi":"https://doi.org/10.1109/waspaa52581.2021.9632740","title":"Learning Multi-Pitch Estimation from Weakly Aligned Score-Audio Pairs Using a Multi-Label CTC Loss","display_name":"Learning Multi-Pitch Estimation from Weakly Aligned Score-Audio Pairs Using a Multi-Label CTC Loss","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4200250820","doi":"https://doi.org/10.1109/waspaa52581.2021.9632740"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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":null,"display_name":"Christof Weiss","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Christof Weiss","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":0.4617,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63418563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9973000288009644,"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":0.814279317855835},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6322404742240906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.618790328502655},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6068618893623352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5590596795082092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4600841999053955},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4417960047721863},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43650075793266296},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3495587706565857},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3465859889984131},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14078232645988464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08172011375427246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814279317855835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6322404742240906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.618790328502655},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6068618893623352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590596795082092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4600841999053955},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4417960047721863},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43650075793266296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3495587706565857},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3465859889984131},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14078232645988464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08172011375427246},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4587505473","display_name":null,"funder_award_id":"DFG WE6611/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1979654135","https://openalex.org/W2017416504","https://openalex.org/W2096482524","https://openalex.org/W2100816929","https://openalex.org/W2107328928","https://openalex.org/W2110007838","https://openalex.org/W2120160933","https://openalex.org/W2127141656","https://openalex.org/W2144414181","https://openalex.org/W2152937398","https://openalex.org/W2198584637","https://openalex.org/W2523056285","https://openalex.org/W2528613928","https://openalex.org/W2559688696","https://openalex.org/W2560254426","https://openalex.org/W2902303903","https://openalex.org/W2906214917","https://openalex.org/W2917340025","https://openalex.org/W2939988664","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2963045359","https://openalex.org/W2998122716","https://openalex.org/W3003566606","https://openalex.org/W3015783972","https://openalex.org/W3095303521","https://openalex.org/W3096508889","https://openalex.org/W3137158725","https://openalex.org/W3186528344","https://openalex.org/W4293775315","https://openalex.org/W6730401039","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6745987316","https://openalex.org/W6755182157","https://openalex.org/W6780226713","https://openalex.org/W6798836799","https://openalex.org/W6950485904"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2769884427","https://openalex.org/W2088690926"],"abstract_inverted_index":{"Detecting":[0],"the":[1,37,44,91,105],"simultaneous":[2],"activity":[3],"of":[4,39,75,86,90],"pitches":[5],"in":[6,77],"music":[7,15,25],"audio":[8],"recordings":[9],"is":[10,48],"a":[11,50,62,66,87],"central":[12],"task":[13],"within":[14],"processing,":[16],"commonly":[17],"known":[18],"as":[19],"multi-pitch":[20,68,112,132],"estimation":[21,113,133],"or":[22],"frame-wise":[23],"polyphonic":[24],"transcription.":[26],"Deep-learning":[27],"approaches":[28],"recently":[29,97],"achieved":[30],"major":[31],"improvements":[32],"for":[33,52,64,99,111,135],"this":[34,58,81],"task,":[35],"but":[36],"lack":[38],"annotated,":[40],"large-size":[41],"datasets":[42,137],"beyond":[43],"piano":[45],"solo":[46],"scenario":[47],"still":[49],"limitation":[51],"fully":[53],"exploiting":[54],"their":[55],"potential.":[56],"In":[57],"paper,":[59],"we":[60,83,129],"propose":[61],"strategy":[63],"training":[65,126,141],"CNN-based":[67],"estimator":[69],"on":[70,131,150],"weakly":[71,139],"aligned":[72,140,152],"score-audio":[73],"pairs":[74],"pieces":[76],"different":[78],"instrumentations.":[79],"To":[80],"end,":[82],"make":[84],"use":[85],"multi-label":[88],"variant":[89],"connectionist":[92],"temporal":[93],"classification":[94],"loss":[95,107],"(MCTC),":[96],"proposed":[98],"image":[100],"recognition":[101],"tasks.":[102],"We":[103],"re-formalize":[104],"MCTC":[106],"to":[108,119,125],"be":[109],"applicable":[110],"and":[114,123],"perform":[115],"several":[116],"systematic":[117],"experiments":[118],"analyze":[120],"its":[121],"behavior":[122],"robustness":[124],"conditions.":[127],"Finally,":[128],"report":[130],"results":[134],"common":[136],"using":[138],"with":[142],"MCTC,":[143],"which":[144],"performs":[145],"similar":[146],"than":[147],"systems":[148],"trained":[149],"strongly":[151],"scores.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
