{"id":"https://openalex.org/W2407887291","doi":"https://doi.org/10.21437/interspeech.2012-108","title":"Combining bottleneck-BLSTM and semi-supervised sparse NMF for recognition of conversational speech in highly instationary noise","display_name":"Combining bottleneck-BLSTM and semi-supervised sparse NMF for recognition of conversational speech in highly instationary noise","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2407887291","doi":"https://doi.org/10.21437/interspeech.2012-108","mag":"2407887291"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-108","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/doc/1137914/document.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068023895","display_name":"Martin W\u00f6llmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin W\u00f6llmer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"302","last_page":"305"},"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":0.9993000030517578,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9983000159263611,"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":0.7812062501907349},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7618651390075684},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6942477822303772},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5177675485610962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4687146246433258},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4597177505493164},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4161396026611328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37920552492141724},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06400242447853088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812062501907349},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7618651390075684},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6942477822303772},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5177675485610962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4687146246433258},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4597177505493164},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4161396026611328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37920552492141724},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06400242447853088},{"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:10.21437/interspeech.2012-108","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1137914","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137914","pdf_url":"http://mediatum.ub.tum.de/doc/1137914/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.6033","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.6033","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/12/12wen9.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1137914","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137914","pdf_url":"http://mediatum.ub.tum.de/doc/1137914/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2407887291.pdf","grobid_xml":"https://content.openalex.org/works/W2407887291.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W2074808018","https://openalex.org/W2112118016","https://openalex.org/W2112865675","https://openalex.org/W2127851351","https://openalex.org/W2155531311","https://openalex.org/W2336741987"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,50,57,63,70],"speaker":[3],"independent":[4],"automatic":[5],"recognition":[6],"of":[7,56,72],"spontaneous":[8],"speech":[9,23],"in":[10,83,86],"highly":[11,88],"variable":[12],"noise":[13,51],"by":[14,36],"applying":[15],"semisupervised":[16],"sparse":[17],"non-negative":[18],"matrix":[19],"factorization":[20],"(NMF)":[21],"for":[22],"enhancement":[24,74],"coupled":[25],"with":[26,62],"our":[27,46],"recently":[28],"proposed":[29],"frontend":[30],"utilizing":[31],"bottleneck":[32],"(BN)":[33],"features":[34],"generated":[35],"a":[37],"bidirectional":[38],"Long":[39],"Short-Term":[40],"Memory":[41],"(BLSTM)":[42],"recurrent":[43],"neural":[44],"network.In":[45],"evaluation,":[47],"we":[48,67],"unite":[49],"corpus":[52],"and":[53,66,75,80],"evaluation":[54],"protocol":[55],"2011":[58],"PASCAL":[59],"CHiME":[60],"challenge":[61],"Buckeye":[64],"database,":[65],"demonstrate":[68],"that":[69],"combination":[71],"NMF":[73],"BN-BLSTM":[76],"front-end":[77],"introduces":[78],"significant":[79],"consistent":[81],"gains":[82],"word":[84],"accuracy":[85],"this":[87],"challenging":[89],"task":[90],"at":[91],"signal-to-noise":[92],"ratios":[93],"from":[94],"-6":[95],"to":[96],"9":[97],"dB.":[98]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
