{"id":"https://openalex.org/W80311640","doi":"https://doi.org/10.21437/interspeech.2004-171","title":"Speech recognition error analysis on the English MALACH corpus","display_name":"Speech recognition error analysis on the English MALACH corpus","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W80311640","doi":"https://doi.org/10.21437/interspeech.2004-171","mag":"80311640"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["IBM, ,"],"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM, ,"],"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["IBM, ,"],"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005881531"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.00946764,"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":"413","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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":0.7979743480682373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458043098449707},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7205559015274048},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6217762231826782},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6201818585395813},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.496081680059433},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4940233826637268},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.47581321001052856},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47335052490234375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44037243723869324},{"id":"https://openalex.org/keywords/speech-error","display_name":"Speech error","score":0.41869622468948364},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4133508801460266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31088927388191223},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26681095361709595},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.23570042848587036},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.13310104608535767},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10128769278526306}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7979743480682373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458043098449707},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7205559015274048},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6217762231826782},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6201818585395813},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.496081680059433},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4940233826637268},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.47581321001052856},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47335052490234375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44037243723869324},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.41869622468948364},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4133508801460266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31088927388191223},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26681095361709595},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.23570042848587036},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.13310104608535767},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10128769278526306},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.645","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/gzweig/pubs/icslp04b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W28535437","https://openalex.org/W82292940","https://openalex.org/W121382850","https://openalex.org/W1480053707","https://openalex.org/W1504694836","https://openalex.org/W1571223402","https://openalex.org/W2065361420","https://openalex.org/W2115002762","https://openalex.org/W2125055259","https://openalex.org/W2126597753","https://openalex.org/W2127923419","https://openalex.org/W2151534206","https://openalex.org/W2155775462"],"related_works":["https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835","https://openalex.org/W2784059283","https://openalex.org/W4399657781"],"abstract_inverted_index":{"This":[0,66,102],"paper":[1,103],"presents":[2],"an":[3,12,23],"analysis":[4],"of":[5,15,31,40,46,55],"the":[6,16,29,56,61,78,107,110,120],"word":[7],"recognition":[8,80,100],"error":[9],"rate":[10],"on":[11,113],"English":[13],"subset":[14],"MALACH":[17,20],"corpus.":[18],"The":[19,38],"project":[21],"is":[22,42,93],"NSF-funded":[24],"research":[25],"program":[26],"related":[27],"to":[28,34,105],"development":[30],"multilingual":[32],"access":[33],"large":[35,44],"audio":[36],"archives.":[37],"archive":[39],"interest":[41],"a":[43,94],"collection":[45],"testimonies":[47],"from":[48],"52,000":[49],"survivors,":[50],"liberators,":[51],"rescuers":[52],"and":[53,123],"witnesses":[54],"Nazi":[57],"Holocaust,":[58],"assembled":[59],"by":[60],"Shoah":[62],"Visual":[63],"History":[64],"Foundation.":[65],"data":[67],"has":[68],"some":[69],"unique":[70],"characteristics":[71],"that":[72,114,119],"make":[73],"it":[74,92],"quite":[75],"unusual":[76],"in":[77],"speech":[79,99],"community":[81],"such":[82],"as":[83],"elderly":[84],"speech,":[85],"noisy":[86],"conditions,":[87],"heavily":[88],"accented":[89],"speech.":[90],"Hence,":[91],"challenging":[95],"task":[96],"for":[97],"automatic":[98],"(ASR).":[101],"attempts":[104],"identify":[106],"factors":[108],"affecting":[109],"ASR":[111],"performance":[112],"task.":[115],"It":[116],"was":[117],"found":[118],"signal-to-noise":[121],"ratio":[122],"syllable":[124]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}