{"id":"https://openalex.org/W115166522","doi":"https://doi.org/10.21437/interspeech.2004-637","title":"A factorial HMM aproach to robust isolated digit recognition in background music","display_name":"A factorial HMM aproach to robust isolated digit recognition in background music","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W115166522","doi":"https://doi.org/10.21437/interspeech.2004-637","mag":"115166522"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-637","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045181882","display_name":"Ameya N. Deoras","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ameya Deoras","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004778663"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01389649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2093","last_page":"2096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9987000226974487,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8647820949554443},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7704273462295532},{"id":"https://openalex.org/keywords/digit-recognition","display_name":"Digit recognition","score":0.7367920875549316},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6104629635810852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5746059417724609},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5683832764625549},{"id":"https://openalex.org/keywords/numerical-digit","display_name":"Numerical digit","score":0.5363162159919739},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5156444311141968},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49431276321411133},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.4932498335838318},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.43716496229171753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4120582938194275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3432219922542572},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.16015851497650146},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10243475437164307}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8647820949554443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7704273462295532},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.7367920875549316},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6104629635810852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5746059417724609},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5683832764625549},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.5363162159919739},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5156444311141968},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49431276321411133},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.4932498335838318},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.43716496229171753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120582938194275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3432219922542572},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.16015851497650146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10243475437164307},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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":"doi:10.21437/interspeech.2004-637","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1528056001","https://openalex.org/W2114548037","https://openalex.org/W2125838338","https://openalex.org/W2130322773","https://openalex.org/W2146608839","https://openalex.org/W2152131029","https://openalex.org/W2160679028","https://openalex.org/W2168793898","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2911525106","https://openalex.org/W4322746633","https://openalex.org/W2736239746","https://openalex.org/W2169083538","https://openalex.org/W2397763568","https://openalex.org/W4398154895","https://openalex.org/W1945018945","https://openalex.org/W3154661292","https://openalex.org/W3037127226","https://openalex.org/W4367793605"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,40,61],"novel":[4],"solution":[5],"to":[6,25,60],"the":[7,28,71,86],"problem":[8],"of":[9,31,39,45,63,83,88],"isolated":[10,89],"digit":[11,41],"recognition":[12,87],"in":[13,79,85,91],"background":[14,92],"music.":[15,46,93],"A":[16],"Factorial":[17],"Hidden":[18],"Markov":[19],"Model":[20],"(FHMM)":[21],"architecture":[22],"is":[23,49],"proposed":[24,72],"accurately":[26],"model":[27],"simultaneous":[29],"occurrence":[30],"two":[32],"independent":[33],"processes,":[34],"such":[35],"as":[36],"an":[37,43,75],"utterance":[38],"and":[42],"excerpt":[44],"The":[47],"FHMM":[48],"implemented":[50],"with":[51],"its":[52],"equivalent":[53],"HMM":[54],"by":[55],"extending":[56],"Nadas\u2019":[57],"MIXMAX":[58],"algorithm":[59],"mixture":[62],"Gaussians":[64],"PDF.":[65],"At":[66],"around":[67],"0":[68],"dB":[69],"SNR,":[70],"system":[73],"shows":[74],"average":[76],"relative":[77],"reduction":[78],"word":[80],"error":[81],"rate":[82],"57%":[84],"digits":[90]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}