{"id":"https://openalex.org/W3215366012","doi":null,"title":"Tuning Sphinx to outperform Google\u2019s speech recognition API","display_name":"Tuning Sphinx to outperform Google\u2019s speech recognition API","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W3215366012","mag":"3215366012"},"language":"en","primary_location":{"id":"mag:3215366012","doi":null,"is_oa":false,"landing_page_url":"https://www.essv.de/paper.php?id=182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5029778136","display_name":"Patrick L. Lange","orcid":"https://orcid.org/0000-0003-3935-663X","observed_orcids":["https://orcid.org/0000-0003-3935-663X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Lange","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008930900","display_name":"David Suendermann\u2010Oeft","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Suendermann\u2010Oeft","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":1.6612,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87177419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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/T12031","display_name":"Speech and dialogue systems","score":0.003000000026077032,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spoken-dialogue-systems","display_name":"spoken dialogue systems","score":0.9100000262260437},{"id":"https://openalex.org/keywords/domain-specific-language-models","display_name":"domain-specific language models","score":0.7429999709129333},{"id":"https://openalex.org/keywords/parameter-tuning","display_name":"parameter tuning","score":0.6769999861717224},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.9049999713897705}],"concepts":[{"id":"https://openalex.org/C2777299493","wikidata":"https://www.wikidata.org/wiki/Q151480","display_name":"Sphinx","level":2,"score":0.9845452308654785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8548810482025146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6687418818473816},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5887182354927063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5007169246673584},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49912405014038086},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47798365354537964},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.47014620900154114},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.45897287130355835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4566551446914673},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1493319571018219},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3215366012","doi":null,"is_oa":false,"landing_page_url":"https://www.essv.de/paper.php?id=182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W110378321","https://openalex.org/W185310710","https://openalex.org/W1508665521","https://openalex.org/W1524333225","https://openalex.org/W1535259248","https://openalex.org/W1595187495","https://openalex.org/W1928047241","https://openalex.org/W1967676196","https://openalex.org/W2005434739","https://openalex.org/W2134950286","https://openalex.org/W2148122154","https://openalex.org/W2156885227","https://openalex.org/W2163238203","https://openalex.org/W2163537793","https://openalex.org/W2166799778","https://openalex.org/W2167662839","https://openalex.org/W2171278097","https://openalex.org/W2185463554","https://openalex.org/W2396066869","https://openalex.org/W2398538125","https://openalex.org/W2905489173"],"related_works":["https://openalex.org/W76440213","https://openalex.org/W6990952561","https://openalex.org/W191416105","https://openalex.org/W2884465151","https://openalex.org/W2596075132","https://openalex.org/W68994212","https://openalex.org/W4234359775","https://openalex.org/W3104005603","https://openalex.org/W7204002269","https://openalex.org/W1480366595"],"abstract_inverted_index":{"In":[0],"this":[1,29],"paper,":[2],"we":[3,32,74],"investigate":[4],"whether":[5],"the":[6,50,64,86],"open-source":[7],"speech":[8,18,47,91],"recognizer":[9],"Sphinx":[10],"can":[11],"be":[12],"tuned":[13],"to":[14,28],"outperform":[15],"Google\u2019s":[16,90],"cloud-based":[17],"recognition":[19,92],"API":[20,93],"in":[21,49],"a":[22,59,69,76],"spoken":[23],"dialog":[24,53],"system":[25,41,54],"task.":[26],"According":[27],"target":[30],"domain,":[31],"use":[33],"data":[34],"from":[35],"CMU\u2019s":[36],"Let\u2019s":[37],"Go":[38],"bus":[39,51],"information":[40,52],"comprising":[42],"258k":[43],"utterances":[44],"of":[45,55,71,78,101],"telephony":[46],"recorded":[48],"Pittsburgh.":[56],"By":[57],"training":[58,104],"domain-specific":[60],"language":[61,95],"model":[62,96],"on":[63,99],"aforementioned":[65],"corpus":[66],"and":[67],"tuning":[68],"number":[70],"Sphinx\u2019s":[72],"parameters,":[73],"achieve":[75],"WER":[77],"51.2%.":[79],"This":[80],"result":[81],"is":[82,97],"significantly":[83],"lower":[84],"than":[85],"one":[87],"produced":[88],"by":[89],"whose":[94],"built":[98],"millions":[100],"times":[102],"more":[103],"data.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2021-12-06T00:00:00"}