{"id":"https://openalex.org/W2613787955","doi":"https://doi.org/10.1109/iscslp.2016.7918416","title":"Interaural coherence induced ideal binary mask for binaural speech separation and dereverberation","display_name":"Interaural coherence induced ideal binary mask for binaural speech separation and dereverberation","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2613787955","doi":"https://doi.org/10.1109/iscslp.2016.7918416","mag":"2613787955"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100348255","display_name":"Yi-Ting Chen","orcid":"https://orcid.org/0000-0001-6748-6832"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Ting Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053774403","display_name":"Tzu-Hao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Hao Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044182477","display_name":"Mao-Chang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mao-Chang Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22456758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7805113792419434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7107173204421997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6149882674217224},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.56183260679245},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5457907319068909},{"id":"https://openalex.org/keywords/interaural-time-difference","display_name":"Interaural time difference","score":0.5417969226837158},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4936178922653198},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.47056862711906433},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46460622549057007},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43717458844184875},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.430886447429657},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.4111473560333252},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3685188889503479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3231545686721802},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2048306167125702},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06930920481681824}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7805113792419434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107173204421997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6149882674217224},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.56183260679245},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5457907319068909},{"id":"https://openalex.org/C103364767","wikidata":"https://www.wikidata.org/wiki/Q1807562","display_name":"Interaural time difference","level":3,"score":0.5417969226837158},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4936178922653198},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.47056862711906433},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46460622549057007},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43717458844184875},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.430886447429657},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.4111473560333252},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3685188889503479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3231545686721802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2048306167125702},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06930920481681824},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320336555","display_name":"Garron Family Cancer Centre","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1586342741","https://openalex.org/W1832112969","https://openalex.org/W1963970749","https://openalex.org/W1965227178","https://openalex.org/W1973746598","https://openalex.org/W1979099822","https://openalex.org/W1989364685","https://openalex.org/W1998648683","https://openalex.org/W2006129368","https://openalex.org/W2027701650","https://openalex.org/W2081869077","https://openalex.org/W2085191029","https://openalex.org/W2105921478","https://openalex.org/W2122171611","https://openalex.org/W2144404214","https://openalex.org/W2161336374","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W4389240440","https://openalex.org/W2060534021","https://openalex.org/W4383197910","https://openalex.org/W2530097559","https://openalex.org/W2025500868","https://openalex.org/W4221151007","https://openalex.org/W2790330717","https://openalex.org/W2952389570","https://openalex.org/W1571453037","https://openalex.org/W3081268946"],"abstract_inverted_index":{"We":[0],"have":[1],"proposed":[2,68],"a":[3,31,42,127],"spatial-cue":[4],"based":[5],"binaural":[6,36,72,95],"noise":[7],"reduction":[8],"algorithm":[9,34,69],"for":[10,35,71],"hearing":[11,73],"aids.":[12,74],"However,":[13],"in":[14],"that":[15],"algorithm,":[16],"decision":[17],"parameters":[18],"are":[19,90],"empirically":[20],"selected.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"extend":[26],"the":[27,49,63,67,81,93,98,102,111,116,135,151],"work":[28],"and":[29,39,52,80,114,140],"propose":[30],"supervised":[32],"classification":[33],"speech":[37],"enhancement/separation":[38],"dereverberation":[40],"using":[41],"modified":[43],"ideal":[44],"binary":[45],"mask":[46],"(mIBM)":[47],"as":[48,57,92],"training":[50,115],"target":[51,112],"simple":[53,64],"neural":[54],"networks":[55],"(NNs)":[56],"classifiers.":[58],"The":[59,75],"low":[60],"complexity":[61],"of":[62,86,100],"NNs":[65],"makes":[66],"practical":[70],"interaural":[76,82,103],"time":[77],"difference":[78,84],"(ITD)":[79],"level":[83],"(ILD)":[85],"each":[87],"T-F":[88],"unit":[89],"extracted":[91],"basic":[94],"features.":[96],"For":[97,118,137],"purpose":[99],"dereverberation,":[101,141],"coherence":[104],"(IC)":[105],"is":[106],"also":[107],"considered":[108],"when":[109],"building":[110],"mIBM":[113],"NNs.":[117],"separation":[119,139],"evaluations,":[120],"our":[121,142],"method":[122,143],"yields":[123],"comparable":[124],"performance":[125],"to":[126,146],"more":[128],"complicated":[129],"benchmark":[130],"system,":[131],"which":[132],"cannot":[133],"de-reverb":[134],"signal.":[136],"concurrent":[138],"offers":[144],"4":[145],"5":[147],"dB":[148],"improvement":[149],"on":[150],"frequency-weighted":[152],"segmental":[153],"speech-to-noise":[154],"ratio":[155],"(SNRfw)":[156],"over":[157],"unprocessed":[158],"speech.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}