{"id":"https://openalex.org/W2397728357","doi":"https://doi.org/10.21437/interspeech.2015-597","title":"Joint training of speech separation, filterbank and acoustic model for robust automatic speech recognition","display_name":"Joint training of speech separation, filterbank and acoustic model for robust automatic speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2397728357","doi":"https://doi.org/10.21437/interspeech.2015-597","mag":"2397728357"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-597","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2974,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89639088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2839","last_page":"2843"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.7905138731002808},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7747724652290344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024614810943604},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6683524250984192},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5097419619560242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.341586172580719},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2333487570285797},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1250409483909607},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.05900818109512329}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7905138731002808},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7747724652290344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024614810943604},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6683524250984192},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5097419619560242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.341586172580719},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2333487570285797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1250409483909607},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.05900818109512329},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-597","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1969851134","https://openalex.org/W1979482308","https://openalex.org/W1989364685","https://openalex.org/W1992475611","https://openalex.org/W2009934439","https://openalex.org/W2015337779","https://openalex.org/W2017608047","https://openalex.org/W2033310064","https://openalex.org/W2035576074","https://openalex.org/W2041638389","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2063224314","https://openalex.org/W2069681747","https://openalex.org/W2072128103","https://openalex.org/W2101045344","https://openalex.org/W2114719288","https://openalex.org/W2137075158","https://openalex.org/W2141411743","https://openalex.org/W2143612262","https://openalex.org/W2146502635","https://openalex.org/W2163922914","https://openalex.org/W2187519021","https://openalex.org/W2213952365","https://openalex.org/W2394967684","https://openalex.org/W2404926044"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W2021595906","https://openalex.org/W100620283","https://openalex.org/W1530808388","https://openalex.org/W4366179611"],"abstract_inverted_index":{"Robustness":[0],"is":[1],"crucial":[2],"for":[3,127],"automatic":[4],"speech":[5,20,56,88],"recognition":[6],"systems":[7],"in":[8,100],"real-world":[9],"environments.":[10],"Speech":[11],"enhancement/separation":[12],"algorithms":[13,25],"are":[14],"normally":[15],"used":[16,117],"to":[17,43,66],"enhance":[18],"noisy":[19,140],"before":[21],"recognition.":[22],"However,":[23],"such":[24],"typically":[26],"introduce":[27],"distortions":[28],"unseen":[29],"by":[30,90,153],"acoustic":[31,63,92,102,128],"models.":[32],"In":[33,94],"this":[34,45],"study,":[35],"we":[36,52,121],"propose":[37],"a":[38,55,59,68,106],"novel":[39],"joint":[40],"training":[41,50],"approach":[42],"reduce":[44],"distortion":[46],"problem.":[47],"At":[48],"the":[49,80,91,96,101,110,115,139,149],"stage,":[51],"first":[53],"concatenate":[54],"separation":[57,81],"DNN,":[58],"filterbank":[60,84],"and":[61,71,83,112,141],"an":[62],"model":[64,103],"DNN":[65],"form":[67],"deeper":[69],"network,":[70],"then":[72],"jointly":[73],"train":[74],"all":[75],"of":[76],"them.":[77],"This":[78],"way,":[79],"frontend":[82,111],"can":[85,104],"provide":[86],"enhanced":[87],"desired":[89],"model.":[93],"addition,":[95],"linguistic":[97],"information":[98],"contained":[99],"have":[105],"positive":[107],"effect":[108],"on":[109,138],"filberbank.":[113],"Besides":[114],"commonly":[116],"log":[118],"mel-spectrogram":[119],"feature,":[120],"also":[122],"add":[123],"more":[124],"robust":[125],"features":[126],"modeling.":[129],"Our":[130],"system":[131],"obtains":[132],"14.1%":[133],"average":[134],"word":[135],"error":[136],"rate":[137],"reverberant":[142],"CHIME-2":[143],"corpus":[144],"(track":[145],"2),":[146],"which":[147],"outperforms":[148],"previous":[150],"best":[151],"result":[152],"8.4%":[154],"relatively.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}