{"id":"https://openalex.org/W944019869","doi":null,"title":"Music and Speech Analysis Using the 'Bach' Scale Filter-Bank","display_name":"Music and Speech Analysis Using the 'Bach' Scale Filter-Bank","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W944019869","mag":"944019869"},"language":"en","primary_location":{"id":"mag:944019869","doi":null,"is_oa":false,"landing_page_url":"https://etd.iisc.ac.in/handle/2005/592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5090325854","display_name":"G. Ananthakrishnan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"G. Ananthakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5090325854"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0032999999821186066,"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":0.00139999995008111,"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/perceptual-scales","display_name":"perceptual scales","score":0.5630000233650208},{"id":"https://openalex.org/keywords/filter-banks","display_name":"filter banks","score":0.7319999933242798},{"id":"https://openalex.org/keywords/time-frequency-analysis","display_name":"time-frequency analysis","score":0.949999988079071},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"speech segmentation","score":0.75},{"id":"https://openalex.org/keywords/query-by-humming","display_name":"query by humming","score":0.9340000152587891},{"id":"https://openalex.org/keywords/pitch-estimation","display_name":"fundamental frequency estimation","score":0.703000009059906},{"id":"https://openalex.org/keywords/mel-scale","display_name":"Mel scale","score":0.5479999780654907},{"id":"https://openalex.org/keywords/bark-scale","display_name":"Bark scale","score":0.9860000014305115},{"id":"https://openalex.org/keywords/hindi-speech","display_name":"Hindi speech","score":0.47999998927116394},{"id":"https://openalex.org/keywords/english-speech","display_name":"English speech","score":0.8999999761581421},{"id":"https://openalex.org/keywords/music-transcription","display_name":"music transcription","score":0.4009999930858612},{"id":"https://openalex.org/keywords/intonation","display_name":"intonation","score":0.3370000123977661},{"id":"https://openalex.org/keywords/frequency-selection","display_name":"frequency selection","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7300743460655212},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6616878509521484},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6424554586410522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611923336982727},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5660796761512756},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.5306320190429688},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5290711522102356},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4445195496082306},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.42382198572158813},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41878581047058105},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4111579656600952},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.31212466955184937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25683945417404175},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17653441429138184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16395896673202515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16181445121765137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12339034676551819},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11068058013916016},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:944019869","doi":null,"is_oa":false,"landing_page_url":"https://etd.iisc.ac.in/handle/2005/592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W75705169","https://openalex.org/W102255675","https://openalex.org/W157965723","https://openalex.org/W159045711","https://openalex.org/W181056519","https://openalex.org/W198114573","https://openalex.org/W610227989","https://openalex.org/W1494195105","https://openalex.org/W1496562625","https://openalex.org/W1508603446","https://openalex.org/W1514558801","https://openalex.org/W1560013842","https://openalex.org/W1578856370","https://openalex.org/W1860310103","https://openalex.org/W1904486158","https://openalex.org/W1950396994","https://openalex.org/W1951766720","https://openalex.org/W1964219887","https://openalex.org/W1982933732","https://openalex.org/W1999854131","https://openalex.org/W2008806652","https://openalex.org/W2021124266","https://openalex.org/W2027518030","https://openalex.org/W2036351204","https://openalex.org/W2041543977","https://openalex.org/W2066452495","https://openalex.org/W2069737407","https://openalex.org/W2074352761","https://openalex.org/W2076608692","https://openalex.org/W2079237043","https://openalex.org/W2090861223","https://openalex.org/W2091425152","https://openalex.org/W2099111195","https://openalex.org/W2103869314","https://openalex.org/W2110816506","https://openalex.org/W2112111790","https://openalex.org/W2114259387","https://openalex.org/W2120344583","https://openalex.org/W2137075158","https://openalex.org/W2146567324","https://openalex.org/W2148154194","https://openalex.org/W2150783950","https://openalex.org/W2155098255","https://openalex.org/W2169711598","https://openalex.org/W2192975138","https://openalex.org/W2530555171","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W2540498048","https://openalex.org/W2008085189","https://openalex.org/W1940302732","https://openalex.org/W6960113984","https://openalex.org/W42270375","https://openalex.org/W2510946267","https://openalex.org/W123331125","https://openalex.org/W1988239432","https://openalex.org/W2995279479","https://openalex.org/W1936312352"],"abstract_inverted_index":{"The":[0,18,77,157,274,288,315,337,401,417],"aim":[1],"of":[2,15,32,35,55,63,82,115,120,182,227,237,254,286,302,322,326,333,345,354,367,389,414,434,437,441,456,487,499],"this":[3,129],"thesis":[4,78,402],"is":[5,24,40,131,155,179,189,291,462],"to":[6,51,143,224,270,278,406],"de\ufb01ne":[7],"a":[8,25,53,88,93,134,229,235,244,272,292,381,404,425,428,432,435,480],"perceptual":[9,100,212],"scale":[10,23,85,107,201,475,482],"for":[11,43,104,123,147,168,174,209,282,427,483],"the":[12,33,38,61,64,69,80,83,105,161,169,175,187,196,199,206,225,300,304,320,330,334,359,408,457,459,465,473,485],"\u2018Time-Frequency\u2019":[13,331],"analysis":[14],"music":[16,36],"signals.":[17],"equal":[19],"tempered":[20],"\u2018Bach":[21],"\u2019":[22],"suitable":[26,481],"scale,":[27,66],"since":[28],"it":[29,47,138],"covers":[30,79],"most":[31,305],"genres":[34],"and":[37,118,171,217,396,447,450,501],"error":[39,353,366],"equally":[41],"distributed":[42],"each":[44],"semi-tone.":[45],"However,":[46],"may":[48,398],"be":[49,141,248,279,399],"necessary":[50],"allow":[52],"tolerance":[54],"around":[56,165,183,355,368],"50":[57],"cents":[58],"or":[59,232,239,260,264],"half":[60],"interval":[62,70],"Bach":[65,84,106,200,474],"so":[67],"that":[68],"can":[71,247],"accommodate":[72],"other":[73,97,192,210],"common":[74,211],"intonation":[75],"schemes.":[76],"formulation":[81],"\ufb01lter-bank":[86,108,130],"as":[87,215,479],"time-varying":[89],"model.":[90],"It":[91,297,349,489],"makes":[92],"comparative":[94],"study":[95],"with":[96,133,191,258,261],"commonly":[98],"used":[99],"scales.":[101,219],"Two":[102,266],"applications":[103],"are":[109,256,268,276],"also":[110,140],"proposed,":[111],"namely":[112,496],"automated":[113,497],"segmentation":[114,498],"speech":[116,151,500],"signals":[117],"transcription":[119],"singing":[121,257],"voice":[122,394],"query-by-humming":[124],"applications.":[125],"\nEven":[127],"though":[128],"suggested":[132,269],"motivation":[135],"from":[136,160,431],"music,":[137],"could":[139],"applied":[142],"speech.":[144],"A":[145,241],"method":[146,362,405],"automatically":[148],"segmenting":[149],"continuous":[150],"into":[152,234],"phonetic":[153],"units":[154],"proposed.":[156],"results,":[158],"obtained":[159],"proposed":[162,478],"method,":[163],"show":[164],"82%":[166],"accuracy":[167,173],"English":[170],"85%":[172],"Hindi":[176],"databases.":[177],"This":[178],"an":[180,352,365],"improvement":[181],"2":[184],"-3%":[185],"when":[186],"performance":[188,233],"compared":[190],"popular":[193],"methods":[194],"in":[195,243,250,329,343,351,364,493],"literature.":[197],"Interestingly,":[198],"\ufb01lters":[202,207],"perform":[203],"better":[204,342],"than":[205],"designed":[208,277],"scales,":[213],"such":[214],"Mel":[216],"Bark":[218],"\n\u2018Musical":[221],"transcription\u2019":[222],"refers":[223],"process":[226],"converting":[228],"musical":[230,415],"rendering":[231],"set":[236],"symbols":[238],"notations.":[240],"query":[242],"\u2018query-by-humming":[245],"system\u2019":[246],"made":[249,439],"several":[251],"ways,":[252],"some":[253],"which":[255],"words,":[259],"arbitrary":[262],"syllables,":[263],"whistling.":[265],"algorithms":[267,275],"annotate":[271],"query.":[273],"fairly":[280],"robust":[281],"these":[283],"various":[284],"forms":[285],"queries.":[287,452],"\ufb01rst":[289],"algorithm":[290,317,340],"frequency":[293,307,360],"selection":[294],"based":[295,392],"method.":[296],"works":[298,318,341],"on":[299,319,393],"basis":[301,321],"selecting":[303],"likely":[306],"components":[308],"at":[309],"any":[311],"given":[312],"time":[313,338],"instant.":[314],"second":[316],"\ufb01nding":[323],"time-connected":[324],"contours":[325],"high":[327],"energy":[328],"plane":[332],"input":[335],"signal.":[336],"domain":[339,361],"terms":[344],"instantaneous":[346],"pitch":[347],"estimates.":[348],"results":[350,363],"10":[356],"-15%,":[357],"while":[358],"12":[369],"-20%.":[370],"\nA":[371],"song":[372,430,461],"rendered":[373],"by":[374,423,444],"two":[375,411,494],"di\ufb00erent":[376,383,412],"people":[377],"will":[378],"have":[379],"quite":[380],"few":[382],"properties.":[384],"Their":[385],"absolute":[386],"pitches,":[387],"rates":[388],"rendering,":[390],"timbres":[391],"quality":[395],"inaccuracies,":[397],"di\ufb00erent.":[400],"discusses":[403],"quantify":[407],"distance":[409,418],"between":[410],"renderings":[413],"pieces.":[416],"function":[419],"has":[420,476,490],"been":[421,477,491],"evaluated":[422],"attempting":[424],"search":[426],"particular":[429],"database":[433],"size":[436],"315,":[438],"up":[440],"songs":[442],"sung":[443],"both":[445],"male":[446],"female":[448],"singers":[449],"whistled":[451],"Around":[453],"90":[454],"%":[455],"time,":[458],"correct":[460],"found":[463],"among":[464],"top":[466],"\ufb01ve":[467],"best":[468],"choices":[469],"picked.":[470],"\nThus,":[472],"representing":[484],"perception":[486],"music.":[488],"explored":[492],"applications,":[495],"transcription\u2026":[502]},"counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2016-06-24T00:00:00"}