{"id":"https://openalex.org/W2989071425","doi":"https://doi.org/10.1109/ssd.2019.8893280","title":"Improving Turkish Telephone Speech Recognition with Data Augmentation and Out of Domain Data","display_name":"Improving Turkish Telephone Speech Recognition with Data Augmentation and Out of Domain Data","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2989071425","doi":"https://doi.org/10.1109/ssd.2019.8893280","mag":"2989071425"},"language":"en","primary_location":{"id":"doi:10.1109/ssd.2019.8893280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssd.2019.8893280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Multi-Conference on Systems, Signals &amp; Devices (SSD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086014618","display_name":"Zeynep Gulhan Uslu","orcid":null},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]},{"id":"https://openalex.org/I4210141511","display_name":"TUBITAK BILGEM","ror":"https://ror.org/057kvja37","country_code":"TR","type":"government","lineage":["https://openalex.org/I4210141511"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Zeynep Gulhan Uslu","raw_affiliation_strings":["Electronics and Communication Eng. Department, Yildiz Technical University, TUBITAK BILGEM, Istanbul, TURKEY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Communication Eng. Department, Yildiz Technical University, TUBITAK BILGEM, Istanbul, TURKEY","institution_ids":["https://openalex.org/I4101805","https://openalex.org/I4210141511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081154924","display_name":"T\u00fclay Y\u0131ld\u0131r\u0131m","orcid":"https://orcid.org/0000-0001-9993-5583"},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tulay Yildirim","raw_affiliation_strings":["Electronics and Communication Eng. Department, Yildiz Technical University, Istanbul, TURKEY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Communication Eng. Department, Yildiz Technical University, Istanbul, TURKEY","institution_ids":["https://openalex.org/I4101805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.42674374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.793644368648529},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7290439605712891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6817513704299927},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.6547472476959229},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.6185939311981201},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5400195717811584},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5360541343688965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5190982818603516},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46741724014282227},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4643543064594269},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4451347291469574},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42952960729599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42146438360214233},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.317899227142334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1263783872127533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793644368648529},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7290439605712891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6817513704299927},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.6547472476959229},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.6185939311981201},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5400195717811584},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5360541343688965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5190982818603516},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46741724014282227},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4643543064594269},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4451347291469574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42952960729599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42146438360214233},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.317899227142334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1263783872127533},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssd.2019.8893280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssd.2019.8893280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Multi-Conference on Systems, Signals &amp; Devices (SSD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1997449813","https://openalex.org/W2111305191","https://openalex.org/W2160815625","https://openalex.org/W2173629880","https://openalex.org/W2184045248","https://openalex.org/W2288817436","https://openalex.org/W2402146185","https://openalex.org/W2528165401","https://openalex.org/W2600174029","https://openalex.org/W2963812242","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6677326886","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2950022897","https://openalex.org/W2101697354","https://openalex.org/W1538193578","https://openalex.org/W3206636855","https://openalex.org/W2126322296","https://openalex.org/W1538606284","https://openalex.org/W1581704179","https://openalex.org/W2890297197","https://openalex.org/W2888189389"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4,81],"the":[5,60,65,82,115],"effects":[6],"of":[7,13,67,84,105,108,117],"data":[8,15,68,77,89,99],"augmentation":[9,69],"and":[10,35,73],"adding":[11,71,101],"out":[12,107],"domain":[14,109],"on":[16],"Turkish":[17,42],"spontaneous":[18,43],"speech":[19,45],"recognition.":[20],"We":[21,47,63,80,96,112],"apply":[22],"different":[23],"acoustic":[24,57,86],"model":[25,58,87],"training":[26,88,98],"techniques":[27,123],"including":[28,91],"Gaussian":[29],"Mixture":[30],"Models,":[31],"Deep":[32],"Neural":[33,38,52,126],"Network":[34,39,53,127],"Time":[36,50],"Delay":[37,51],"to":[40],"Babel":[41],"telephone":[44],"data.":[46,95,111],"find":[48],"that":[49],"with":[54],"iVectors":[55],"based":[56,120],"performs":[59],"best":[61],"result.":[62],"demonstrate":[64],"effect":[66,83,116],"by":[70,90,100],"speed":[72],"volume":[74],"perturbation":[75],"applied":[76],"in":[78],"training.":[79],"increasing":[85],"two":[92],"call":[93],"center":[94],"increase":[97],"about":[102],"100":[103],"hours":[104],"modified":[106],"broadcast":[110],"also":[113],"examine":[114],"neural":[118],"network":[119],"language":[121,128],"modeling":[122],"like":[124],"Recurrent":[125],"models.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
