{"id":"https://openalex.org/W2135430834","doi":"https://doi.org/10.1109/icassp.2011.5947532","title":"On the use of ideal binary masks for improving phonetic classification","display_name":"On the use of ideal binary masks for improving phonetic classification","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2135430834","doi":"https://doi.org/10.1109/icassp.2011.5947532","mag":"2135430834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"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":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.6239,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69022057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"22","issue":null,"first_page":"5212","last_page":"5215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7873044013977051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7068593502044678},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6768101453781128},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6622932553291321},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6495288610458374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6149880290031433},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5821282267570496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671393871307373},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5257100462913513},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5079348683357239},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48173287510871887},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4810214638710022},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2804897129535675},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.25895723700523376},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1982848346233368},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10000360012054443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873044013977051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7068593502044678},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6768101453781128},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6622932553291321},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6495288610458374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6149880290031433},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5821282267570496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671393871307373},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5257100462913513},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5079348683357239},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48173287510871887},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4810214638710022},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2804897129535675},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25895723700523376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1982848346233368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10000360012054443},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.1427","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.1427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Narayanan-Wang.icassp11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1562289873","https://openalex.org/W1578856370","https://openalex.org/W1871378514","https://openalex.org/W2029177977","https://openalex.org/W2040304231","https://openalex.org/W2077804127","https://openalex.org/W2104997912","https://openalex.org/W2107789863","https://openalex.org/W2115439799","https://openalex.org/W2116284136","https://openalex.org/W2124876722","https://openalex.org/W2131870124","https://openalex.org/W2137094732","https://openalex.org/W2157059077","https://openalex.org/W2165447343","https://openalex.org/W2561557072","https://openalex.org/W2619993508","https://openalex.org/W3021396111","https://openalex.org/W3127686677","https://openalex.org/W3150649775","https://openalex.org/W4233392025","https://openalex.org/W4256399001","https://openalex.org/W6675604347","https://openalex.org/W6676071220","https://openalex.org/W6678615401","https://openalex.org/W6679579573","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2162550210","https://openalex.org/W1494724239","https://openalex.org/W2050397613","https://openalex.org/W2048014685","https://openalex.org/W2057635330","https://openalex.org/W2080458333","https://openalex.org/W1995562189"],"abstract_inverted_index":{"Ideal":[0],"binary":[1,4,23,41],"masks":[2,42],"are":[3],"patterns":[5,24],"that":[6,21,49],"encode":[7],"the":[8,52,58,71,80,86,97,106],"masking":[9],"characteristics":[10],"of":[11,54,82,94],"speech":[12,18,30,65],"in":[13,17],"noise.":[14],"Recent":[15],"evidence":[16],"perception":[19],"suggests":[20],"such":[22],"provide":[25],"sufficient":[26],"information":[27],"for":[28,79],"human":[29],"recognition.":[31],"Motivated":[32],"by":[33,50],"these":[34],"findings,":[35],"we":[36,89],"propose":[37],"to":[38,43],"use":[39],"ideal":[40],"improve":[44],"phonetic":[45,83,99],"modeling.":[46],"We":[47],"show":[48],"combining":[51],"outputs":[53],"classifiers":[55],"trained":[56],"on":[57,96],"traditional":[59],"MFCC":[60,73],"features":[61],"and":[62],"this":[63],"novel":[64],"pattern,":[66],"statistically":[67],"significant":[68],"improvements":[69],"over":[70],"baseline":[72],"based":[74],"classifier":[75],"can":[76],"be":[77],"achieved":[78],"task":[81,101],"classification.":[84],"Using":[85],"combined":[87],"classifiers,":[88],"achieve":[90],"an":[91],"error":[92],"rate":[93],"19.5%":[95],"TIMIT":[98],"classification":[100],"using":[102],"multilayer":[103],"perceptrons":[104],"as":[105],"underlying":[107],"classifier.":[108]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}