{"id":"https://openalex.org/W2967218197","doi":"https://doi.org/10.21437/interspeech.2019-1907","title":"Challenging the Boundaries of Speech Recognition: The MALACH Corpus","display_name":"Challenging the Boundaries of Speech Recognition: The MALACH Corpus","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2967218197","doi":"https://doi.org/10.21437/interspeech.2019-1907","mag":"2967218197"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1907","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.03455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zolt\u00e1n T\u00fcske","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034529775"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57552939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.991599977016449,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9901000261306763,"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":0.7659125328063965},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.680206835269928},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.6452953815460205},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6316240429878235},{"id":"https://openalex.org/keywords/speech-community","display_name":"Speech community","score":0.566826581954956},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.5034357905387878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49930834770202637},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4679749310016632},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42972826957702637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42059239745140076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34146884083747864},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.30043625831604004},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2588002681732178},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2379554808139801},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14465388655662537},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.11609303951263428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659125328063965},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.680206835269928},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.6452953815460205},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6316240429878235},{"id":"https://openalex.org/C2779881370","wikidata":"https://www.wikidata.org/wiki/Q383340","display_name":"Speech community","level":2,"score":0.566826581954956},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.5034357905387878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49930834770202637},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4679749310016632},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42972826957702637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42059239745140076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34146884083747864},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30043625831604004},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2588002681732178},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2379554808139801},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14465388655662537},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.11609303951263428},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1907","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.03455","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03455","pdf_url":"https://arxiv.org/pdf/1908.03455","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2967218197","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.03455","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1908.03455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.03455","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.03455","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03455","pdf_url":"https://arxiv.org/pdf/1908.03455","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2967218197.pdf","grobid_xml":"https://content.openalex.org/works/W2967218197.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W15497043","https://openalex.org/W1494198834","https://openalex.org/W2002342963","https://openalex.org/W2024490156","https://openalex.org/W2033310064","https://openalex.org/W2063415950","https://openalex.org/W2095705004","https://openalex.org/W2103584254","https://openalex.org/W2114016253","https://openalex.org/W2125610823","https://openalex.org/W2127923419","https://openalex.org/W2154887136","https://openalex.org/W2155117693","https://openalex.org/W2158195707","https://openalex.org/W2288371874","https://openalex.org/W2403195671","https://openalex.org/W2810381179","https://openalex.org/W2962824709","https://openalex.org/W2962832505","https://openalex.org/W2963266252","https://openalex.org/W2963980299"],"related_works":["https://openalex.org/W2972974544","https://openalex.org/W2103584254","https://openalex.org/W2107755572","https://openalex.org/W3200506395","https://openalex.org/W2011168910","https://openalex.org/W2963765325","https://openalex.org/W3029923669","https://openalex.org/W3145048926","https://openalex.org/W2144588880","https://openalex.org/W2981454799","https://openalex.org/W2051745966","https://openalex.org/W2402747436","https://openalex.org/W2114499288","https://openalex.org/W1533994743","https://openalex.org/W2625808939","https://openalex.org/W2625252387","https://openalex.org/W2246980364","https://openalex.org/W3010812523","https://openalex.org/W2113996750","https://openalex.org/W2405746843"],"abstract_inverted_index":{"There":[0],"has":[1,156],"been":[2,142,158],"huge":[3],"progress":[4],"in":[5,186],"speech":[6,58,66,81,88,113],"recognition":[7,89,114],"over":[8],"the":[9,45,48,57,103,108,130,171,182],"last":[10],"several":[11],"years.":[12],"Tasks":[13],"once":[14],"thought":[15],"extremely":[16,183],"difficult,":[17],"such":[18],"as":[19],"SWITCHBOARD,":[20],"now":[21],"approach":[22],"levels":[23],"of":[24,36,40,47,63,177],"human":[25,97],"performance.":[26],"The":[27,60,154],"MALACH":[28,109],"corpus":[29,110],"(LDC":[30],"catalog":[31],"LDC2012S05),":[32],"a":[33,37,134,195],"375-Hour":[34],"subset":[35],"large":[38],"archive":[39],"Holocaust":[41],"testimonies":[42],"collected":[43],"by":[44,160],"Survivors":[46],"Shoah":[49],"Visual":[50],"History":[51],"Foundation,":[52],"presents":[53],"significant":[54],"challenges":[55],"to":[56,111,122,173,194],"community.":[59],"collection":[61],"consists":[62],"unconstrained,":[64],"natural":[65],"filled":[67],"with":[68,120],"disfluencies,":[69],"heavy":[70],"accents,":[71,123],"age-related":[72],"coarticulations,":[73],"un-cued":[74],"speaker":[75],"and":[76,79,125,136,138,144,188],"language":[77],"switching,":[78],"emotional":[80,126],"-":[82],"all":[83],"still":[84],"open":[85],"problems":[86],"for":[87,95,132],"systems.":[90],"Transcription":[91],"is":[92,164],"challenging":[93],"even":[94],"skilled":[96],"annotators.":[98],"This":[99],"paper":[100],"proposes":[101],"that":[102,116,166,181],"community":[104,172],"place":[105],"focus":[106],"on":[107,175],"develop":[112],"systems":[115],"are":[117,152],"more":[118],"robust":[119],"respect":[121],"disfluencies":[124],"speech.":[127],"To":[128],"reduce":[129],"barrier":[131],"entry,":[133],"lexicon":[135],"training":[137],"testing":[139],"setups":[140],"have":[141],"created":[143],"baseline":[145],"results":[146],"using":[147],"current":[148],"deep":[149],"learning":[150],"technologies":[151],"presented.":[153],"metadata":[155],"just":[157],"released":[159],"LDC":[161],"(LDC2019S11).":[162],"It":[163],"hoped":[165],"this":[167],"resource":[168],"will":[169],"enable":[170],"build":[174],"top":[176],"these":[178,187],"baselines":[179],"so":[180],"important":[184],"information":[185],"related":[189],"oral":[190],"histories":[191],"becomes":[192],"accessible":[193],"wider":[196],"audience.":[197]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}