{"id":"https://openalex.org/W3096509852","doi":"https://doi.org/10.21437/interspeech.2020-1900","title":"Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement","display_name":"Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096509852","doi":"https://doi.org/10.21437/interspeech.2020-1900","mag":"3096509852"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1900","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5042520842","display_name":"Jun Qi","orcid":"https://orcid.org/0000-0001-7533-2630"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jun Qi","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207545","display_name":"Hu Hu","orcid":"https://orcid.org/0000-0002-0009-8218"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu Hu","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Tencent Media Lab, Tencent Corporation, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Media Lab, Tencent Corporation, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]},{"id":"https://openalex.org/I4210127672","display_name":"Engineering (Italy)","ror":"https://ror.org/045s9b323","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210127672"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Computer Engineering School, University of Enna, Italy","Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Engineering School, University of Enna, Italy","institution_ids":["https://openalex.org/I246010334","https://openalex.org/I4210127672"]},{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042520842"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.6669,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8479921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"80"},"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":0.9957000017166138,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9891999959945679,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7675251960754395},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7628381848335266},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6164245009422302},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6065837740898132},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.572776198387146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5438327193260193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4620399475097656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.448172003030777},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43942829966545105},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4383998513221741},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41563108563423157},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15692362189292908},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14155226945877075},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05987820029258728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675251960754395},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7628381848335266},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6164245009422302},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6065837740898132},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.572776198387146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5438327193260193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4620399475097656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.448172003030777},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43942829966545105},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4383998513221741},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41563108563423157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15692362189292908},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14155226945877075},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05987820029258728},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1900","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/636628","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/636628","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1798945469","https://openalex.org/W1897240248","https://openalex.org/W1993482030","https://openalex.org/W2024490156","https://openalex.org/W2044893557","https://openalex.org/W2067584370","https://openalex.org/W2078528584","https://openalex.org/W2117852776","https://openalex.org/W2159202424","https://openalex.org/W2603567530","https://openalex.org/W2626544737","https://openalex.org/W2944332341","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2969649301","https://openalex.org/W2991251958","https://openalex.org/W3014522660","https://openalex.org/W3016132433","https://openalex.org/W3022073510","https://openalex.org/W3023457900","https://openalex.org/W4297781745","https://openalex.org/W4301350573"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4200527723"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"different":[3],"trade-offs":[4],"between":[5],"the":[6,55,71,85,89,104,120,133,141,153,163],"number":[7,154],"of":[8,35,50,88,122,126,140,155,162,170,198],"model":[9,44,75,127,143,165],"parameters":[10,157],"and":[11,64,193,202],"enhanced":[12],"speech":[13,23,62,107,114,172,200],"qualities":[14,201],"by":[15,136],"employing":[16],"several":[17,51],"deep":[18],"tensor-to-vector":[19],"regression":[20,96],"models":[21,195],"for":[22,57],"enhancement.":[24],"We":[25,77],"find":[26],"that":[27,181],"a":[28,37,42,65,80,123,175],"hybrid":[29,184],"architecture,":[30],"namely":[31],"CNN-TT,":[32],"is":[33,48,158],"capable":[34],"maintaining":[36],"good":[38],"quality":[39,63],"performance":[40,147],"with":[41],"reduced":[43],"parameter":[45,204],"size.":[46,166],"CNN-TT":[47,130,156,185],"composed":[49],"convolutional":[52,90],"layers":[53],"at":[54,119],"bottom":[56],"feature":[58],"extraction":[59],"to":[60,73,109,160],"improve":[61],"tensor-train":[66],"(TT)":[67],"output":[68],"layer":[69],"on":[70,84,103,174],"top":[72],"reduce":[74],"parameters.":[76,144],"first":[78],"derive":[79],"new":[81],"upper":[82],"bound":[83],"generalization":[86],"power":[87],"neural":[91],"network":[92],"(CNN)":[93],"based":[94],"vector-to-vector":[95],"models.":[97],"Then,":[98],"we":[99],"provide":[100],"experimental":[101],"evidence":[102],"Edinburgh":[105],"noisy":[106,177],"corpus":[108,179],"demonstrate":[110,180],"that,":[111],"in":[112,196],"single-channel":[113],"enhancement,":[115],"CNN":[116,134,142,164,194],"outperforms":[117,132],"DNN":[118,192],"expense":[121],"small":[124],"increment":[125],"sizes.":[128,205],"Besides,":[129,145],"slightly":[131],"counterpart":[135],"utilizing":[137],"only":[138],"32%":[139],"further":[146],"improvement":[148],"can":[149],"be":[150],"attained":[151],"if":[152],"increased":[159],"44%":[161],"Finally,":[167],"our":[168,182],"experiments":[169],"multi-channel":[171],"enhancement":[173],"simulated":[176],"WSJ0":[178],"proposed":[183],"architecture":[186],"achieves":[187],"better":[188],"results":[189],"than":[190],"both":[191],"terms":[197],"better-enhanced":[199],"smaller":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}