{"id":"https://openalex.org/W3134777296","doi":"https://doi.org/10.1109/iscslp49672.2021.9362112","title":"Phase Spectrum Recovery for Enhancing Low-Quality Speech Captured by Laser Microphones","display_name":"Phase Spectrum Recovery for Enhancing Low-Quality Speech Captured by Laser Microphones","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3134777296","doi":"https://doi.org/10.1109/iscslp49672.2021.9362112","mag":"3134777296"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th 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/A5101896376","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-8072-5815"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chang Liu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101896376"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39864773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"32","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":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/T11447","display_name":"Blind Source Separation Techniques","score":0.987500011920929,"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":0.9864000082015991,"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/pesq","display_name":"PESQ","score":0.8309462070465088},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7965429425239563},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7568299770355225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.730797290802002},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7210382223129272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6046729683876038},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5380864143371582},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.5056843757629395},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4290539026260376},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4246065318584442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3345850110054016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15502750873565674},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14209356904029846},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12185248732566833},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11822256445884705},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07984673976898193},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.058234989643096924}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8309462070465088},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7965429425239563},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7568299770355225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730797290802002},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7210382223129272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6046729683876038},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5380864143371582},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.5056843757629395},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4290539026260376},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4246065318584442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3345850110054016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15502750873565674},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14209356904029846},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12185248732566833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11822256445884705},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07984673976898193},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.058234989643096924},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th 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","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1968939597","https://openalex.org/W2044893557","https://openalex.org/W2058079016","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2105768884","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2605589342","https://openalex.org/W2937484199","https://openalex.org/W2963452667","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2972404066","https://openalex.org/W2972910332","https://openalex.org/W2991015288","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6751512325","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","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":{"This":[0],"paper":[1,51],"proposes":[2],"a":[3,43,53,67,93],"phase":[4,68,106],"spectrum":[5,38,63,69],"recovery":[6],"method":[7,135,143],"for":[8],"enhancing":[9],"the":[10,109,113,116,123,142,148],"low-quality":[11],"speech":[12,32,54,99,126,150],"captured":[13],"by":[14,20],"laser":[15],"micro-phones,":[16],"which":[17,57],"is":[18,58],"degraded":[19],"non-additive":[21],"distortions":[22],"during":[23],"signal":[24],"acquisition.":[25],"Our":[26,128],"preliminary":[27],"study":[28],"shows":[29],"that":[30,132],"common":[31],"enhancement":[33,55,151],"methods":[34],"based":[35],"on":[36,46],"amplitude":[37,62,84],"estimation":[39],"can":[40,136],"not":[41],"achieve":[42,137],"satisfactory":[44],"performance":[45],"this":[47,50],"task.":[48],"Therefore,":[49],"designs":[52],"model":[56,95],"comprised":[59],"of":[60,115],"an":[61],"estimator":[64,70],"(ASE)":[65],"and":[66,77,103,147,155],"(PSE).":[71],"The":[72,89],"ASE":[73,146],"adopts":[74,92],"autoregressive":[75],"LSTMs":[76],"multi-target":[78],"learning":[79],"framework":[80],"to":[81,96,121],"predict":[82],"clean":[83],"spectra":[85,107],"from":[86,108],"noisy":[87,98],"ones.":[88],"PSE":[90],"first":[91],"waveform-based":[94,149],"enhance":[97],"in":[100],"time":[101],"domain,":[102],"then":[104],"extracts":[105],"enhanced":[110,125],"waveforms.":[111,127],"Subsequently,":[112],"outputs":[114],"two":[117],"estimators":[118],"are":[119],"combined":[120],"reconstruct":[122],"final":[124],"experimental":[129],"results":[130],"demonstrate":[131],"our":[133],"proposed":[134],"higher":[138],"PESQ":[139],"score":[140],"than":[141],"using":[144],"only":[145],"methods,":[152],"including":[153],"UNet":[154],"TCNN.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}