{"id":"https://openalex.org/W1989674786","doi":"https://doi.org/10.1109/asru.2013.6707748","title":"Elastic spectral distortion for low resource speech recognition with deep neural networks","display_name":"Elastic spectral distortion for low resource speech recognition with deep neural networks","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1989674786","doi":"https://doi.org/10.1109/asru.2013.6707748","mag":"1989674786"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Central Research Laboratory, Hitachi Ltd., Tokyo, Kokubunji-shi, Japan","Central Res. Lab., Hitachi, Ltd., Kokubunji, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Research Laboratory, Hitachi Ltd., Tokyo, Kokubunji-shi, Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Central Res. Lab., Hitachi, Ltd., Kokubunji, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018403421","display_name":"Ryu Takeda","orcid":"https://orcid.org/0009-0007-0518-6245"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryu Takeda","raw_affiliation_strings":["Central Research Laboratory, Hitachi Ltd., Tokyo, Kokubunji-shi, Japan","Central Res. Lab., Hitachi, Ltd., Kokubunji, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Research Laboratory, Hitachi Ltd., Tokyo, Kokubunji-shi, Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Central Res. Lab., Hitachi, Ltd., Kokubunji, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113670873","display_name":"Yasunari Obuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasunari Obuchi","raw_affiliation_strings":["Central Research Laboratory, Hitachi Ltd., Tokyo, Kokubunji-shi, Japan","Central Res. Lab., Hitachi, Ltd., Kokubunji, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Research Laboratory, Hitachi Ltd., Tokyo, Kokubunji-shi, Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Central Res. Lab., Hitachi, Ltd., Kokubunji, Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":4.3473,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.95536891,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.998199999332428,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8184780478477478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7749530076980591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7141698002815247},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6753730773925781},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6413111090660095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5764155387878418},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5193772912025452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49395495653152466},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4871377646923065},{"id":"https://openalex.org/keywords/phase-distortion","display_name":"Phase distortion","score":0.4395589232444763},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.413079172372818},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13101887702941895},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07637041807174683}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8184780478477478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7749530076980591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141698002815247},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6753730773925781},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6413111090660095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5764155387878418},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5193772912025452},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49395495653152466},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4871377646923065},{"id":"https://openalex.org/C57747864","wikidata":"https://www.wikidata.org/wiki/Q7180948","display_name":"Phase distortion","level":3,"score":0.4395589232444763},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.413079172372818},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13101887702941895},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07637041807174683},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1498436455","https://openalex.org/W1875231349","https://openalex.org/W1993660824","https://openalex.org/W1993882792","https://openalex.org/W2000200144","https://openalex.org/W2013598660","https://openalex.org/W2044577954","https://openalex.org/W2062227835","https://openalex.org/W2099621636","https://openalex.org/W2120209245","https://openalex.org/W2136922672","https://openalex.org/W2144792281","https://openalex.org/W2146502635","https://openalex.org/W2156163116","https://openalex.org/W2160306971","https://openalex.org/W2163605009","https://openalex.org/W2172097686","https://openalex.org/W2394932179","https://openalex.org/W2618530766","https://openalex.org/W6601785968","https://openalex.org/W6639350448","https://openalex.org/W6648822320","https://openalex.org/W6675409298","https://openalex.org/W6681435938","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2626065499","https://openalex.org/W4245698648","https://openalex.org/W2116460786","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2074878601","https://openalex.org/W2026402306","https://openalex.org/W2033273300"],"abstract_inverted_index":{"An":[0],"acoustic":[1],"model":[2],"based":[3],"on":[4],"hidden":[5],"Markov":[6],"models":[7],"with":[8,75,87,97,111],"deep":[9],"neural":[10],"networks":[11],"(DNN-HMM)":[12],"has":[13],"recently":[14],"been":[15],"proposed":[16],"and":[17,66,71],"achieved":[18,103],"high":[19],"recognition":[20,85],"accuracy.":[21],"In":[22,79],"this":[23],"paper,":[24],"we":[25],"investigated":[26,54],"an":[27],"elastic":[28,99],"spectral":[29,100],"distortion":[30,56,69,101],"method":[31,102],"to":[32,37],"artificially":[33],"augment":[34],"training":[35,51,92],"samples":[36],"help":[38],"DNN-HMMs":[39],"acquire":[40],"enough":[41],"robustness":[42],"even":[43],"when":[44],"there":[45],"are":[46],"a":[47,80,94,104,112],"limited":[48],"number":[49],"of":[50,91],"samples.":[52],"We":[53],"three":[55],"methods":[57,74],"-":[58,70],"vocal":[59],"tract":[60],"length":[61],"distortion,":[62,65],"speech":[63,84],"rate":[64],"frequency-axis":[67],"random":[68],"evaluated":[72],"those":[73],"Japanese":[76],"lecture":[77],"recordings.":[78],"large":[81],"vocabulary":[82],"continuous":[83],"task":[86],"only":[88],"10":[89],"hours":[90],"samples,":[93],"DNN-HMM":[95],"trained":[96,114],"the":[98],"10.1%":[105],"relative":[106],"word":[107],"error":[108],"reduction":[109],"compared":[110],"normally":[113],"DNN-HMM.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}