{"id":"https://openalex.org/W4238331033","doi":"https://doi.org/10.1109/icme.2003.1221390","title":"Robust digit recognition using phase-dependent time-frequency masking","display_name":"Robust digit recognition using phase-dependent time-frequency masking","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W4238331033","doi":"https://doi.org/10.1109/icme.2003.1221390"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5003286836","display_name":"G. Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"G. Shi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044141602","display_name":"P. Aarabi","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"P. Aarabi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003286836"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.2928,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63220046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"III","last_page":"629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11447","display_name":"Blind Source Separation Techniques","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":0.9995999932289124,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7081505060195923},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.697669267654419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6658227443695068},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.562818169593811},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5105756521224976},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5014605522155762},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49542129039764404},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4921361804008484},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44930392503738403},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.43807467818260193},{"id":"https://openalex.org/keywords/numerical-digit","display_name":"Numerical digit","score":0.4252103567123413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35695767402648926},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34893369674682617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2930726408958435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21016442775726318},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19669881463050842},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08905535936355591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081505060195923},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.697669267654419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6658227443695068},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.562818169593811},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5105756521224976},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5014605522155762},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49542129039764404},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4921361804008484},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44930392503738403},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.43807467818260193},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.4252103567123413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35695767402648926},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34893369674682617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2930726408958435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21016442775726318},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19669881463050842},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08905535936355591},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1221390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1506558619","https://openalex.org/W1560013842","https://openalex.org/W1977167953","https://openalex.org/W2108384452","https://openalex.org/W2110130611","https://openalex.org/W2114863372","https://openalex.org/W2123649031","https://openalex.org/W2482792214","https://openalex.org/W6644815614","https://openalex.org/W6677383040"],"related_works":["https://openalex.org/W2380293945","https://openalex.org/W1974812937","https://openalex.org/W1500522817","https://openalex.org/W3095239554","https://openalex.org/W3212409750","https://openalex.org/W4387088887","https://openalex.org/W1972023576","https://openalex.org/W2072053180","https://openalex.org/W1541088746","https://openalex.org/W4319862450"],"abstract_inverted_index":{"A":[0],"technique":[1,35],"using":[2,18,36],"the":[3,22,33],"time-frequency":[4,16],"phase":[5],"information":[6],"of":[7,21,24,31,52],"two":[8,37,65,80],"microphones":[9,38,66,81],"is":[10],"proposed":[11,34],"to":[12],"estimate":[13],"an":[14],"ideal":[15],"mask":[17],"time-delay-of-arrival":[19],"(TDOA)":[20],"signal":[23],"interest.":[25],"At":[26],"a":[27,40,60,75],"signal-to-noise":[28],"ratio":[29],"(SNR)":[30],"0dB,":[32],"achieves":[39,59,74],"digit":[41],"recognition":[42,62,77],"rate":[43,63,78],"(average":[44],"over":[45],"5":[46],"speakers,":[47],"each":[48],"speaking":[49],"20-30":[50],"digits)":[51],"71%.":[53],"In":[54],"contrast,":[55],"delay-and-sum":[56],"beamforming":[57,73],"only":[58],"40%":[61],"with":[64,69,79,84],"and":[67,82],"60%":[68],"four":[70,85],"microphones.":[71,86],"Superdirective":[72],"44%":[76],"65%":[83]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
