{"id":"https://openalex.org/W2291743162","doi":"https://doi.org/10.1109/asru.2015.7404835","title":"Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition","display_name":"Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2291743162","doi":"https://doi.org/10.1109/asru.2015.7404835","mag":"2291743162"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067036469","display_name":"Ning Ma","orcid":"https://orcid.org/0000-0002-4112-3109"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080527909","display_name":"Guy J. Brown","orcid":"https://orcid.org/0000-0001-8565-5476"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy J. Brown","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"490","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/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":0.9993000030517578,"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":0.7450590133666992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7181782126426697},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6358184218406677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6015293002128601},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6012259125709534},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5560076236724854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5101071000099182},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48311352729797363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4693770408630371},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.45787569880485535},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44876644015312195},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4383623003959656}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7450590133666992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181782126426697},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6358184218406677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6015293002128601},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6012259125709534},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5560076236724854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5101071000099182},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48311352729797363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693770408630371},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45787569880485535},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44876644015312195},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4383623003959656},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2015.7404835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04931730v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04931730","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Dec 2015, Scottsdale, United States. pp.490-495, ⟨10.1109/ASRU.2015.7404835⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:eprints.whiterose.ac.uk:102984","is_oa":false,"landing_page_url":"http://eprints.whiterose.ac.uk/102984/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1550695516","https://openalex.org/W1550985492","https://openalex.org/W1779452081","https://openalex.org/W1863426813","https://openalex.org/W1985371235","https://openalex.org/W2026369565","https://openalex.org/W2042141988","https://openalex.org/W2044222806","https://openalex.org/W2050758723","https://openalex.org/W2062164080","https://openalex.org/W2067117291","https://openalex.org/W2075774708","https://openalex.org/W2094461119","https://openalex.org/W2128653836","https://openalex.org/W2140595311","https://openalex.org/W2141411743","https://openalex.org/W2148613904","https://openalex.org/W2160815625","https://openalex.org/W2289394825","https://openalex.org/W2290318471","https://openalex.org/W2402146185","https://openalex.org/W4297797495","https://openalex.org/W6631362777","https://openalex.org/W6638005537","https://openalex.org/W6681118392","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,41,55,69,116,129],"novel":[4],"system":[5,114],"that":[6,89],"exploits":[7],"synchrony":[8,91],"spectra":[9,25,92],"and":[10,45,127],"deep":[11],"neural":[12],"networks":[13],"(DNNs)":[14],"for":[15,57,68],"automatic":[16],"speech":[17],"recognition":[18],"(ASR)":[19],"in":[20,34,54,78],"challenging":[21],"noisy":[22],"environments.":[23],"Synchrony":[24],"measure":[26],"the":[27,65,79,82,90,98,102,108,134],"extent":[28],"to":[29,40,63,101,107],"which":[30],"each":[31],"frequency":[32],"channel":[33],"an":[35],"auditory":[36],"model":[37],"is":[38],"entrained":[39],"particular":[42],"pitch":[43],"period,":[44],"they":[46],"are":[47],"used":[48],"together":[49],"with":[50],"F0":[51],"estimates":[52],"either":[53],"DNN":[56],"time-frequency":[58],"(T-M)":[59],"mask":[60],"estimation":[61],"or":[62],"augment":[64],"input":[66,99],"features":[67,93,100],"DNN-based":[70,103],"ASR":[71,104],"system.":[72,105],"The":[73],"proposed":[74],"approach":[75],"was":[76],"evaluated":[77],"context":[80],"of":[81,122,131],"CHiME":[83],"3":[84],"Challenge.":[85],"Our":[86],"experiments":[87],"show":[88],"work":[94],"best":[95,113],"when":[96],"augmenting":[97],"Compared":[106],"CHiME-3":[109],"baseline":[110],"system,":[111],"our":[112],"provides":[115],"word":[117],"error":[118],"rate":[119],"(WER)":[120],"reduction":[121],"more":[123],"than":[124],"14%":[125],"absolute":[126],"achieved":[128],"WER":[130],"18.56%":[132],"on":[133],"evaluation":[135],"test":[136],"set.":[137]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}