{"id":"https://openalex.org/W2887580030","doi":"https://doi.org/10.1109/hsi.2018.8431366","title":"Acoustic Data Building Toolset for Easy Experimentation with Neural Network-based Speech Recognition in Polish and English","display_name":"Acoustic Data Building Toolset for Easy Experimentation with Neural Network-based Speech Recognition in Polish and English","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2887580030","doi":"https://doi.org/10.1109/hsi.2018.8431366","mag":"2887580030"},"language":"en","primary_location":{"id":"doi:10.1109/hsi.2018.8431366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi.2018.8431366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Conference on Human System Interaction (HSI)","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/A5109903143","display_name":"Jerzy Sas","orcid":null},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Jerzy Sas","raw_affiliation_strings":["Faculty of Computer Science and Management, Wroclaw University of Science and Technology, Wroclaw, POLAND"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Management, Wroclaw University of Science and Technology, Wroclaw, POLAND","institution_ids":["https://openalex.org/I11923345"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109903143"],"corresponding_institution_ids":["https://openalex.org/I11923345"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08754836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9843000173568726,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8603850603103638},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8352245092391968},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6882932782173157},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5900474190711975},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5444257855415344},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5351921319961548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4822138547897339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4724346101284027},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44728463888168335},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4472004771232605},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4390580952167511},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42654597759246826},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31099122762680054},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2292332947254181},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.17772790789604187},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1604054570198059},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09040006995201111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603850603103638},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8352245092391968},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6882932782173157},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5900474190711975},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5444257855415344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5351921319961548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4822138547897339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724346101284027},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44728463888168335},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4472004771232605},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4390580952167511},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42654597759246826},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31099122762680054},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2292332947254181},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.17772790789604187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1604054570198059},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09040006995201111},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hsi.2018.8431366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi.2018.8431366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Conference on Human System Interaction (HSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W1608367484","https://openalex.org/W1990005915","https://openalex.org/W1993882792","https://openalex.org/W2106051978","https://openalex.org/W2125964738","https://openalex.org/W2160815625","https://openalex.org/W2620589393","https://openalex.org/W2963963943","https://openalex.org/W6679053740","https://openalex.org/W6739082035"],"related_works":["https://openalex.org/W3127686677","https://openalex.org/W80423236","https://openalex.org/W2189142582","https://openalex.org/W2808291730","https://openalex.org/W2140130847","https://openalex.org/W2397167112","https://openalex.org/W3012168345","https://openalex.org/W2015876361","https://openalex.org/W1961523962","https://openalex.org/W2105439218"],"abstract_inverted_index":{"In":[0,149],"this":[1,126,150],"paper":[2,127],"the":[3,7,14,26,54,62,66,111,114,145],"CLARIN-PHONEREC":[4],"toolset":[5],"for":[6,71,154,163],"conversion":[8,98],"of":[9,17,25,91,113],"an":[10],"acoustic":[11,59],"corpus":[12,60],"into":[13],"loadable":[15],"set":[16],"Python":[18,41],"binary":[19,63],"arrays":[20],"is":[21,28,108],"described.":[22],"The":[23,105,122],"aim":[24],"tools":[27,85,123],"to":[29,33,61,68,95,99,132,159],"make":[30,47],"it":[31],"easy":[32],"start":[34],"experimenting":[35],"with":[36],"automatic":[37],"speech":[38,72,96,119],"recognition":[39,73,135],"using":[40,83],"and":[42,79,86,102,137],"neural":[43],"networks":[44],"libraries.":[45],"To":[46],"initial":[48],"experiments":[49,74],"even":[50],"easier,":[51],"apart":[52],"from":[53,110,144],"programs":[55],"that":[56],"convert":[57],"any":[58],"shape,":[64],"also":[65,130],"ready":[67],"use":[69],"datasets":[70],"in":[75,125,140],"Polish":[76,118,155],"are":[77,89],"provided":[78,84,106],"described":[80],"here.":[81],"By":[82],"datasets,":[87],"researchers":[88],"free":[90],"heavy":[92],"labour":[93],"related":[94],"sample":[97],"train,":[100],"development":[101],"test":[103],"datasets.":[104],"dataset":[107],"created":[109],"one":[112],"biggest":[115],"publicly":[116],"available":[117],"corpora:":[120],"CLARIN-PL.":[121],"presented":[124],"can":[128,156],"be":[129,157],"used":[131],"prepare":[133],"phoneme":[134],"training":[136],"testing":[138],"data":[139],"other":[141],"languages,":[142],"e.g.":[143],"popular":[146],"TIMIT":[147],"dataset.":[148],"way,":[151],"experiment":[152],"results":[153,161],"compared":[158],"analogous":[160],"obtained":[162],"English.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}