{"id":"https://openalex.org/W1991904167","doi":"https://doi.org/10.1109/icassp.2014.6854052","title":"Analysis-by-synthesis feature estimation for robust automatic speech recognition using spectral masks","display_name":"Analysis-by-synthesis feature estimation for robust automatic speech recognition using spectral masks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1991904167","doi":"https://doi.org/10.1109/icassp.2014.6854052","mag":"1991904167"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael I Mandel","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University","Ohio State University"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University","Ohio State University"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043596676"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.5823,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65262427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"2509","last_page":"2513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7938463687896729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793457508087158},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7037747502326965},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5793595314025879},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5736867785453796},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5650128126144409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5402408242225647},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.520176887512207},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4928767681121826},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48950302600860596},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48261818289756775},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47843483090400696},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4752975404262543},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4558197259902954},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.430133581161499},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41839683055877686},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1810576617717743}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7938463687896729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793457508087158},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7037747502326965},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5793595314025879},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5736867785453796},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5650128126144409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5402408242225647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.520176887512207},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4928767681121826},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48950302600860596},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48261818289756775},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47843483090400696},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4752975404262543},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4558197259902954},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.430133581161499},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41839683055877686},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1810576617717743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W71792008","https://openalex.org/W93048866","https://openalex.org/W160800111","https://openalex.org/W943204654","https://openalex.org/W1492775261","https://openalex.org/W1560013842","https://openalex.org/W1963970749","https://openalex.org/W1967590528","https://openalex.org/W2035576074","https://openalex.org/W2039844283","https://openalex.org/W2057889776","https://openalex.org/W2062518906","https://openalex.org/W2074354966","https://openalex.org/W2077658674","https://openalex.org/W2103825654","https://openalex.org/W2110402487","https://openalex.org/W2136833314","https://openalex.org/W2141411743","https://openalex.org/W2143855671","https://openalex.org/W2144404214","https://openalex.org/W2154291215","https://openalex.org/W2164240509","https://openalex.org/W2399251227","https://openalex.org/W3035139526","https://openalex.org/W4212997115","https://openalex.org/W6659187427","https://openalex.org/W6779487094"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2066371342"],"abstract_inverted_index":{"Spectral":[0],"masking":[1,39],"is":[2,30],"a":[3,62,87],"promising":[4],"method":[5],"for":[6],"noise":[7,19],"suppression":[8],"in":[9],"which":[10],"regions":[11,23,100],"of":[12,68,74,89,101],"the":[13,41,66,75,90,93,99,102,107,110,125],"spectrogram":[14],"that":[15,85],"are":[16,20,27,83],"dominated":[17,24],"by":[18,25,106],"attenuated":[21],"while":[22],"speech":[26,48,58,77,120,128,147],"preserved.":[28],"It":[29],"not":[31],"clear,":[32],"however,":[33],"how":[34],"best":[35],"to":[36,45,56,98,145,150],"combine":[37],"spectral":[38,63],"with":[40,131],"non-linear":[42],"processing":[43],"necessary":[44],"compute":[46],"automatic":[47,57],"recognition":[49,129],"features.":[50],"We":[51],"propose":[52],"an":[53,79,115],"analysis-by-synthesis":[54,137],"approach":[55],"recognition,":[59],"which,":[60],"given":[61],"mask,":[64],"poses":[65],"estimation":[67],"mel":[69],"frequency":[70],"cepstral":[71],"coefficients":[72],"(MFCCs)":[73],"clean":[76,95,146],"as":[78,148],"optimization":[80],"problem.":[81],"MFCCs":[82],"found":[84],"minimize":[86],"combination":[88],"distance":[91],"from":[92],"resynthesized":[94],"power":[96],"spectrum":[97,104],"noisy":[103,127],"selected":[105],"mask":[108],"and":[109,134,143],"negative":[111],"log":[112],"likelihood":[113],"under":[114],"unmodified":[116],"large":[117],"vocabulary":[118],"continuous":[119],"recognizer.":[121],"In":[122],"evaluations":[123],"on":[124],"Aurora4":[126],"task":[130],"both":[132,139],"ideal":[133],"estimated":[135],"masks,":[136],"decreases":[138],"word":[140],"error":[141],"rates":[142],"distances":[144],"compared":[149],"traditional":[151],"approaches.":[152]},"counts_by_year":[{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}