{"id":"https://openalex.org/W2115055618","doi":"https://doi.org/10.1109/icassp.2013.6638983","title":"Feature enhancement by bidirectional LSTM networks for conversational speech recognition in highly non-stationary noise","display_name":"Feature enhancement by bidirectional LSTM networks for conversational speech recognition in highly non-stationary noise","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2115055618","doi":"https://doi.org/10.1109/icassp.2013.6638983","mag":"2115055618"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5068023895","display_name":"Martin W\u00f6llmer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156768","display_name":"BMW Group (Germany)","ror":"https://ror.org/044kkbh92","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Wollmer","raw_affiliation_strings":["BMW Group, Munich, Germany","BMW Group; Munich Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BMW Group, Munich, Germany","institution_ids":["https://openalex.org/I4210156768"]},{"raw_affiliation_string":"BMW Group; Munich Germany","institution_ids":["https://openalex.org/I4210156768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6822","last_page":"6826"},"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":0.9997000098228455,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.8187203407287598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7406361103057861},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.62595534324646},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.597184419631958},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5711089372634888},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5170005559921265},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.48493340611457825},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48395732045173645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47189339995384216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4717201590538025},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.41767480969429016},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4117436408996582},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.163129985332489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187203407287598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7406361103057861},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.62595534324646},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.597184419631958},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5711089372634888},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5170005559921265},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.48493340611457825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48395732045173645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189339995384216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4717201590538025},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.41767480969429016},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4117436408996582},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.163129985332489},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2013.6638983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.1640","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.1640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ//pdf/13/13woe2.pdf","raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71519","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-715190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"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":30,"referenced_works":["https://openalex.org/W2012897754","https://openalex.org/W2064675550","https://openalex.org/W2074671152","https://openalex.org/W2074808018","https://openalex.org/W2079735306","https://openalex.org/W2112118016","https://openalex.org/W2115109087","https://openalex.org/W2120987913","https://openalex.org/W2131774270","https://openalex.org/W2133340843","https://openalex.org/W2135029798","https://openalex.org/W2136848157","https://openalex.org/W2141520175","https://openalex.org/W2147437692","https://openalex.org/W2148577181","https://openalex.org/W2155531311","https://openalex.org/W2162753443","https://openalex.org/W2164597369","https://openalex.org/W2166880842","https://openalex.org/W2168826081","https://openalex.org/W2341993073","https://openalex.org/W2407887291","https://openalex.org/W2587486463","https://openalex.org/W2761561469","https://openalex.org/W2799238042","https://openalex.org/W3143596294","https://openalex.org/W6669042365","https://openalex.org/W6680012447","https://openalex.org/W6704128869","https://openalex.org/W6733190831"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2109916967","https://openalex.org/W2890297197","https://openalex.org/W2101697354","https://openalex.org/W1538193578","https://openalex.org/W3206636855","https://openalex.org/W1538606284","https://openalex.org/W2373874059"],"abstract_inverted_index":{"The":[0],"recognition":[1,57,89],"of":[2,28,66,145],"spontaneous":[3,147],"speech":[4,39,83,102,148],"in":[5,42,137,140],"highly":[6,142],"variable":[7],"noise":[8],"is":[9,92],"known":[10],"to":[11,48,81,95,116,134],"be":[12],"a":[13,141],"challenge,":[14],"especially":[15],"at":[16,149],"low":[17],"signal-to-noise":[18],"ratios":[19],"(SNR).":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"investigate":[25],"the":[26,56,87],"effect":[27],"applying":[29],"bidirectional":[30],"Long":[31],"Short-Term":[32],"Memory":[33],"(BLSTM)":[34],"recurrent":[35,125],"neural":[36,52,126],"networks":[37,46,74],"for":[38,77],"feature":[40,110,121,130],"enhancement":[41,103,122,131],"noisy":[43,80],"conditions.":[44],"BLSTM":[45,73],"tend":[47],"prevail":[49],"over":[50],"conventional":[51],"network":[53],"architectures,":[54],"whenever":[55],"or":[58,120],"regression":[59],"task":[60,144],"relies":[61],"on":[62],"an":[63],"intelligent":[64],"exploitation":[65],"temporal":[67],"context":[68],"information.":[69],"We":[70],"show":[71],"that":[72,86],"are":[75],"well-suited":[76],"mapping":[78],"from":[79],"clean":[82],"features":[84],"and":[85,108,154],"obtained":[88],"performance":[90],"gain":[91],"partly":[93],"complementary":[94],"improvements":[96],"via":[97,123],"additional":[98],"techniques":[99],"such":[100],"as":[101],"by":[104,112],"non-negative":[105],"matrix":[106],"factorization":[107],"probabilistic":[109],"generation":[111],"Bottleneck-BLSTM":[113],"networks.":[114],"Compared":[115],"simple":[117],"multi-condition":[118],"training":[119],"standard":[124],"networks,":[127],"our":[128],"BLSTM-based":[129],"approach":[132],"leads":[133],"remarkable":[135],"gains":[136],"word":[138],"accuracy":[139],"challenging":[143],"recognizing":[146],"SNR":[150],"levels":[151],"between":[152],"-6":[153],"9":[155],"dB.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}