{"id":"https://openalex.org/W2750380122","doi":"https://doi.org/10.21437/interspeech.2017-187","title":"Tight Integration of Spatial and Spectral Features for BSS with Deep Clustering Embeddings","display_name":"Tight Integration of Spatial and Spectral Features for BSS with Deep Clustering Embeddings","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2750380122","doi":"https://doi.org/10.21437/interspeech.2017-187","mag":"2750380122"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-187","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5011191228","display_name":"Lukas Drude","orcid":"https://orcid.org/0000-0003-3683-5432"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lukas Drude","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011191228"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.397,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97936935,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2650","last_page":"2654"},"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":0.9984999895095825,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6793062686920166},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6229695081710815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867987334728241},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3652103543281555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6793062686920166},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6229695081710815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867987334728241},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3652103543281555}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-187","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1552314771","https://openalex.org/W1978752674","https://openalex.org/W1981463705","https://openalex.org/W1987906574","https://openalex.org/W2003203076","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2095705004","https://openalex.org/W2098723113","https://openalex.org/W2131774270","https://openalex.org/W2143027228","https://openalex.org/W2145001205","https://openalex.org/W2150415460","https://openalex.org/W2150593711","https://openalex.org/W2155515171","https://openalex.org/W2158143227","https://openalex.org/W2221409856","https://openalex.org/W2289480995","https://openalex.org/W2295335497","https://openalex.org/W2403319665","https://openalex.org/W2408321390","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2563666542","https://openalex.org/W2702006285","https://openalex.org/W2949117887","https://openalex.org/W2962715207"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2163831990","https://openalex.org/W3003836766","https://openalex.org/W2046077695","https://openalex.org/W2378160586","https://openalex.org/W2042327336","https://openalex.org/W2996038082","https://openalex.org/W3047965787","https://openalex.org/W3184582087"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,116,155,189],"discriminatively":[3,45],"trained":[4,46],"mask":[5],"estimation":[6],"networks":[7,26],"to":[8,60,68,159,182],"extract":[9],"a":[10,29,76,92,106,136,141,151,172],"single":[11],"source":[12,58],"utilizing":[13],"beamforming":[14,143,152],"techniques":[15],"demonstrate,":[16],"that":[17,130,177],"the":[18,117,131,178],"integration":[19],"of":[20,87,157],"statistical":[21,56,77],"models":[22],"and":[23,62,112,145,163],"deep":[24,88,109,137],"neural":[25],"(DNNs)":[27],"are":[28],"promising":[30],"approach":[31],"for":[32,108],"robust":[33],"automatic":[34],"speech":[35],"recognition":[36],"(ASR)":[37],"applications.":[38],"In":[39],"this":[40],"contribution":[41],"we":[42],"demonstrate":[43],"how":[44],"embeddings":[47,90,111],"on":[48,91,171],"spectral":[49],"features":[50],"can":[51],"be":[52],"tightly":[53],"integrated":[54,132],"into":[55],"model-based":[57],"separation":[59],"separate":[61,93],"transcribe":[63],"overlapping":[64],"speech.":[65],"Good":[66],"generalization":[67],"unseen":[69],"spatial":[70,114],"configurations":[71],"is":[72],"achieved":[73],"by":[74],"estimating":[75],"model":[78,107,133,139,149],"at":[79,124],"test":[80,125],"time,":[81],"while":[82],"still":[83],"leveraging":[84],"discriminative":[85],"training":[86,94],"clustering":[89,110,138],"set.":[95],"We":[96],"formulate":[97],"an":[98,147],"expectation":[99],"maximization":[100],"(EM)":[101],"algorithm":[102],"which":[103],"jointly":[104],"estimates":[105],"complex-valued":[113],"observations":[115],"short":[118],"time":[119],"Fourier":[120],"transform":[121],"(STFT)":[122],"domain":[123],"time.":[126],"Extensive":[127],"simulations":[128],"confirm,":[129],"outperforms":[134],"(a)":[135],"with":[140,150],"subsequent":[142],"step":[144,153],"(b)":[146],"EM-based":[148],"alone":[154],"terms":[156],"signal":[158],"distortion":[160],"ratio":[161],"(SDR)":[162],"perceptually":[164],"motivated":[165],"metric":[166],"(PESQ)":[167],"gains.":[168],"ASR":[169],"results":[170],"reverberated":[173],"dataset":[174],"further":[175],"show,":[176],"aforementioned":[179],"gains":[180],"translate":[181],"reduced":[183],"word":[184],"error":[185],"rates":[186],"(WERs)":[187],"even":[188],"reverberant":[190],"environments.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}