{"id":"https://openalex.org/W118339868","doi":"https://doi.org/10.21437/interspeech.2004-618","title":"Why speech recognizers make errors ? a robustness view","display_name":"Why speech recognizers make errors ? a robustness view","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W118339868","doi":"https://doi.org/10.21437/interspeech.2004-618","mag":"118339868"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-618","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-618","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/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["Gwangju institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Gwangju institute of Science and Technology","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109219016","display_name":"Mazin G. Rahim","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mazin Rahim","raw_affiliation_strings":["At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085604883"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":1.356,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83366555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1645","last_page":"1648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9983999729156494,"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":0.8317393064498901},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.812045156955719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7359642386436462},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5767612457275391},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5290103554725647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5099591016769409},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43171054124832153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3594440817832947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3503471612930298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317393064498901},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.812045156955719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7359642386436462},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5767612457275391},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5290103554725647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099591016769409},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43171054124832153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3594440817832947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3503471612930298},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-618","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-618","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W22549796","https://openalex.org/W1979012094","https://openalex.org/W2045036776","https://openalex.org/W2109320731","https://openalex.org/W2113981416","https://openalex.org/W2114548037","https://openalex.org/W2119535101","https://openalex.org/W2135445137"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"The":[0,21],"performance":[1],"of":[2,17,51,88,95],"large":[3,49],"vocabulary":[4],"speech":[5,13],"recognizers":[6],"often":[7],"varies":[8],"depending":[9],"on":[10],"the":[11,15,18,101],"input":[12],"and":[14],"quality":[16],"trained":[19],"models.":[20],"particular":[22],"attributes":[23],"that":[24,32,81],"cause":[25],"recognition":[26,89],"errors":[27,90],"are":[28],"a":[29,44,48,64,85,92,105],"research":[30],"area":[31],"has":[33],"not":[34],"been":[35],"well":[36],"studied.":[37],"This":[38],"paper":[39],"addresses":[40],"this":[41,82],"issue":[42],"from":[43,55],"robustness":[45],"perspective":[46],"using":[47],"amount":[50],"field":[52],"data":[53,106],"collected":[54],"natural":[56],"language":[57],"dialog":[58],"services.":[59],"In":[60],"particular,":[61],"we":[62],"present":[63],"method":[65],"for":[66,109],"tracking":[67],"time-varying":[68],"or":[69],"nonstationary":[70],"extraneous":[71],"events,":[72],"such":[73],"as":[74],"music,":[75],"background":[76],"noise,":[77],"etc.":[78],"We":[79],"show":[80],"measure":[83,94],"is":[84],"better":[86],"predictor":[87],"than":[91],"standard":[93],"stationary":[96],"signal-to-noise":[97],"ratio":[98],"(SNR).":[99],"Combining":[100],"two":[102],"measures":[103],"provides":[104],"selection":[107],"algorithm":[108],"detecting":[110],"problematic":[111],"speech.":[112]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}