{"id":"https://openalex.org/W2771813982","doi":"https://doi.org/10.1109/waspaa.2017.8170001","title":"Modulation spectrum based beamforming for speech enhancement","display_name":"Modulation spectrum based beamforming for speech enhancement","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771813982","doi":"https://doi.org/10.1109/waspaa.2017.8170001","mag":"2771813982"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8170001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5027383698","display_name":"Sam Karimian-Azari","orcid":"https://orcid.org/0000-0002-6225-2663"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sam Karimian-Azari","raw_affiliation_strings":["INRS-EMT, University of Quebec, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-EMT, University of Quebec, Montreal, QC, Canada","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065418889","display_name":"Tiago H. Falk","orcid":"https://orcid.org/0000-0002-5739-2514"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tiago H. Falk","raw_affiliation_strings":["INRS-EMT, University of Quebec, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-EMT, University of Quebec, Montreal, QC, Canada","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027383698"],"corresponding_institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66977161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"95"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/pesq","display_name":"PESQ","score":0.8926443457603455},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8032805323600769},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7527147531509399},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6670176386833191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6308759450912476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5466793179512024},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5411658883094788},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5339141488075256},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.41171061992645264},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3530547618865967},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3335687518119812},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.30778801441192627},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2528534531593323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1677233874797821},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15891200304031372},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10895705223083496}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8926443457603455},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8032805323600769},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7527147531509399},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6670176386833191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308759450912476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5466793179512024},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5411658883094788},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5339141488075256},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.41171061992645264},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3530547618865967},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3335687518119812},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.30778801441192627},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2528534531593323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1677233874797821},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15891200304031372},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10895705223083496},{"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/waspaa.2017.8170001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W122386018","https://openalex.org/W653761051","https://openalex.org/W1480055486","https://openalex.org/W1552314771","https://openalex.org/W1555217905","https://openalex.org/W1603978816","https://openalex.org/W1931312565","https://openalex.org/W1987831012","https://openalex.org/W1995536493","https://openalex.org/W1999686891","https://openalex.org/W2030486566","https://openalex.org/W2046317813","https://openalex.org/W2066218102","https://openalex.org/W2121973264","https://openalex.org/W2122431481","https://openalex.org/W2125114513","https://openalex.org/W2130178255","https://openalex.org/W2137075158","https://openalex.org/W2157790793","https://openalex.org/W2163729192","https://openalex.org/W2167783140","https://openalex.org/W3147539069","https://openalex.org/W6604999081"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"In":[0,29,50],"array":[1,94],"signal":[2,95],"processing,":[3],"beamforming":[4],"is":[5,84],"a":[6,39,75],"common":[7],"technique":[8],"to":[9,20,42,64,79,86,97,129],"align":[10,87],"time":[11,88],"differences":[12,89],"between":[13,90],"multi-microphone":[14],"signals.":[15,105],"Beamformers,":[16],"however,":[17],"have":[18],"limits":[19],"reduce":[21],"noise":[22,101],"specially":[23],"in":[24,82,131,138],"the":[25,51,72,93,99,103,116,121,132],"presence":[26],"of":[27,36,71,92,102,141],"reverberation.":[28],"this":[30],"paper,":[31],"we":[32,62],"incorporate":[33],"modulation":[34,52,117],"properties":[35],"speech":[37,142],"into":[38,57],"pre-processing":[40,76,118],"algorithm":[41],"improve":[43],"beamformer":[44,126],"performance":[45],"under":[46],"combined":[47],"noise-plus-reverberation":[48,112],"conditions.":[49],"domain,":[53],"signals":[54],"are":[55],"decomposed":[56],"modulators":[58],"and":[59,66,96,111,135],"carriers.":[60],"Here,":[61],"propose":[63],"filter":[65],"perform":[67],"short-time":[68],"spectral":[69],"subtraction":[70],"modulator":[73],"as":[74],"step":[77],"prior":[78],"beamforming,":[80],"which":[81],"turn,":[83],"designed":[85],"carriers":[91],"minimize":[98],"residual":[100],"pre-processed":[104],"Simulation":[106],"results":[107],"with":[108],"several":[109],"noise-only":[110],"conditions":[113],"show":[114],"that":[115],"has":[119],"improved":[120],"minimum":[122],"power":[123],"distortionless":[124],"response":[125],"by":[127],"up":[128],"7.4dB":[130],"signal-to-noise":[133],"ratio":[134],"0.6":[136],"points":[137],"perceptual":[139],"evaluation":[140],"quality":[143],"(PESQ)":[144],"score.":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}