{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T03:05:48Z","timestamp":1768014348802,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T00:00:00Z","timestamp":1575244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,12,2]]},"DOI":"10.1145\/3366030.3366083","type":"proceedings-article","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T12:18:47Z","timestamp":1582373927000},"page":"136-141","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Accent neutralization for speech recognition of non-native speakers"],"prefix":"10.1145","author":[{"given":"Kacper","family":"Radzikowski","sequence":"first","affiliation":[{"name":"Waseda University Graduate School of Information, Production and Systems, Kitakyushu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mateusz","family":"Forc","sequence":"additional","affiliation":[{"name":"Warsaw University of Technology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[{"name":"Waseda University Graduate School of Information, Production and Systems, Kitakyushu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osamu","family":"Yoshie","sequence":"additional","affiliation":[{"name":"Waseda University Graduate School of Information, Production and Systems, Kitakyushu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Nowak","sequence":"additional","affiliation":[{"name":"Warsaw University of Technology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"e_1_3_2_1_3_1","unstructured":"Dario Amodei Rishita Anubhai Eric Battenberg Carl Case Jared Casper Bryan Catanzaro Jingdong Chen Mike Chrzanowski Adam Coates Greg Diamos Erich Elsen Jesse Engel Linxi Fan Christopher Fougner Tony Han Awni Hannun Billy Jun Patrick LeGresley Libby Lin Sharan Narang Andrew Ng Sherjil Ozair Ryan Prenger Jonathan Raiman Sanjeev Satheesh David Seetapun Shubho Sengupta Yi Wang Zhiqian Wang Chong Wang Bo Xiao Dani Yogatama Jun Zhan and Zhenyao Zhu. 2015. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin. arXiv:arXiv:1512.02595  Dario Amodei Rishita Anubhai Eric Battenberg Carl Case Jared Casper Bryan Catanzaro Jingdong Chen Mike Chrzanowski Adam Coates Greg Diamos Erich Elsen Jesse Engel Linxi Fan Christopher Fougner Tony Han Awni Hannun Billy Jun Patrick LeGresley Libby Lin Sharan Narang Andrew Ng Sherjil Ozair Ryan Prenger Jonathan Raiman Sanjeev Satheesh David Seetapun Shubho Sengupta Yi Wang Zhiqian Wang Chong Wang Bo Xiao Dani Yogatama Jun Zhan and Zhenyao Zhu. 2015. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin. arXiv:arXiv:1512.02595"},{"key":"e_1_3_2_1_4_1","unstructured":"P.W.D. Charles. 2019. keras. https:\/\/github.com\/charlespwd\/project-title.  P.W.D. Charles. 2019. keras. https:\/\/github.com\/charlespwd\/project-title."},{"key":"e_1_3_2_1_5_1","volume-title":"International Journal for Advance Research in Engineering and Technology 1 (7","author":"Dave N","year":"2013","unstructured":"N Dave . 2013. Feature extraction methods lpc, plp and mfcc in speech recognition . International Journal for Advance Research in Engineering and Technology 1 (7 2013 ), 1--5. N Dave. 2013. Feature extraction methods lpc, plp and mfcc in speech recognition. International Journal for Advance Research in Engineering and Technology 1 (7 2013), 1--5."},{"key":"e_1_3_2_1_6_1","first-page":"4","article-title":"Front-End Factor Analysis for Speaker","volume":"19","author":"Dehak R. Dehak N., Kenny","year":"2011","unstructured":"Dehak R. Dehak N., Kenny P. J. and Ouellet P. Dumouchel P. 2011 . Front-End Factor Analysis for Speaker Verification. Trans. Audio, Speech and Lang. Proc. 19 , 4 (May 2011), 788--798. https:\/\/doi.org\/10.1109\/TASL.2010.2064307 10.1109\/TASL.2010.2064307 Dehak R. Dehak N., Kenny P. J. and Ouellet P. Dumouchel P. 2011. Front-End Factor Analysis for Speaker Verification. Trans. Audio, Speech and Lang. Proc. 19, 4 (May 2011), 788--798. https:\/\/doi.org\/10.1109\/TASL.2010.2064307","journal-title":"Verification. Trans. Audio, Speech and Lang. Proc."},{"key":"e_1_3_2_1_7_1","unstructured":"Leon A. Gatys Alexander S. Ecker and Matthias Bethge. 2015. A Neural Algorithm of Artistic Style. arXiv:arXiv:1508.06576  Leon A. Gatys Alexander S. Ecker and Matthias Bethge. 2015. A Neural Algorithm of Artistic Style. arXiv:arXiv:1508.06576"},{"key":"#cr-split#-e_1_3_2_1_8_1.1","doi-asserted-by":"crossref","unstructured":"Eric Grinstein Ngoc Duong Alexey Ozerov and Patrick P\u00c3l'rez. 2017. Audio style transfer. (2017). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461711 arXiv:arXiv:1710.11385 10.1109\/ICASSP.2018.8461711","DOI":"10.1109\/ICASSP.2018.8461711"},{"key":"#cr-split#-e_1_3_2_1_8_1.2","doi-asserted-by":"crossref","unstructured":"Eric Grinstein Ngoc Duong Alexey Ozerov and Patrick P\u00c3l'rez. 2017. Audio style transfer. (2017). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461711 arXiv:arXiv:1710.11385","DOI":"10.1109\/ICASSP.2018.8461711"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Justin Johnson Alexandre Alahi and Li Fei-Fei. 2016. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. arXiv:arXiv:1603.08155  Justin Johnson Alexandre Alahi and Li Fei-Fei. 2016. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. arXiv:arXiv:1603.08155","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_10_1","volume-title":"Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Computer Speech Language","author":"Narayanan S.","year":"2013","unstructured":"Narayanan S. Li M., Han K. J. 2013. Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Computer Speech Language ( 2013 ). Narayanan S. Li M., Han K. J. 2013. Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Computer Speech Language (2013)."},{"key":"e_1_3_2_1_11_1","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Livescu K.","year":"2000","unstructured":"K. Livescu and J. Glass . 2000. Lexical modeling of non-native speech for automatic speech recognition . IEEE International Conference on Acoustics, Speech and Signal Processing ( 2000 ). K. Livescu and J. Glass. 2000. Lexical modeling of non-native speech for automatic speech recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (2000)."},{"key":"e_1_3_2_1_12_1","volume-title":"Fifteenth Annual Conference of the International Speech Communication Association.","author":"Metallinou Angeliki","year":"2014","unstructured":"Angeliki Metallinou and Jian Cheng . 2014 . Using deep neural networks to improve proficiency assessment for children English language learners . In Fifteenth Annual Conference of the International Speech Communication Association. Angeliki Metallinou and Jian Cheng. 2014. Using deep neural networks to improve proficiency assessment for children English language learners. In Fifteenth Annual Conference of the International Speech Communication Association."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-018-0146-4"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the conference of institute of electrical engineers of japan, electronics and information systems division","author":"Radzikowski Kacper Yoshie Osamu","year":"2017","unstructured":"Yoshie Osamu Radzikowski Kacper , Wang Le . 2017 . Non-native speech recognition using characteristic speech features, with respect to nationality . Proceedings of the conference of institute of electrical engineers of japan, electronics and information systems division (2017). Yoshie Osamu Radzikowski Kacper, Wang Le. 2017. Non-native speech recognition using characteristic speech features, with respect to nationality. Proceedings of the conference of institute of electrical engineers of japan, electronics and information systems division (2017)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the Conference of Institute of Electrical Engineers of Japan, Electronics and Information Systems Division.","author":"Kacper Radzikowski","year":"2016","unstructured":"Radzikowski Kacper , Wang Le , Yoshie Osamu . 2016 . Non-native English speaker's speech correction, based on domain focused document . In Proceedings of the Conference of Institute of Electrical Engineers of Japan, Electronics and Information Systems Division. Radzikowski Kacper, Wang Le, Yoshie Osamu. 2016. Non-native English speaker's speech correction, based on domain focused document. In Proceedings of the Conference of Institute of Electrical Engineers of Japan, Electronics and Information Systems Division."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services (iiWAS '16)","author":"Kacper Radzikowski","year":"2016","unstructured":"Radzikowski Kacper , Wang Le , Yoshie Osamu . 2016 . Non-native English Speakers' Speech Correction, Based on Domain Focused Document . In Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services (iiWAS '16) . ACM, New York, NY, USA, 276--281. https:\/\/doi.org\/10.1145\/3011141.3011169 10.1145\/3011141.3011169 Radzikowski Kacper, Wang Le, Yoshie Osamu. 2016. Non-native English Speakers' Speech Correction, Based on Domain Focused Document. In Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services (iiWAS '16). ACM, New York, NY, USA, 276--281. https:\/\/doi.org\/10.1145\/3011141.3011169"},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. Interspeech","author":"Drugman T. Dutoit T.","year":"2009","unstructured":"T. Dutoit T. Drugman . 2009 . Glottal closure and opening instant detection from speech signals . Proc. Interspeech (2009). T. Dutoit T. Drugman. 2009. Glottal closure and opening instant detection from speech signals. Proc. Interspeech (2009)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. ICASSP","author":"Tan T.","year":"2007","unstructured":"T. Tan and L. Besacier . 2007. Acoustic model interpolation for non-native speech recognition . Proc. ICASSP ( 2007 ). T. Tan and L. Besacier. 2007. Acoustic model interpolation for non-native speech recognition. Proc. ICASSP (2007)."},{"key":"e_1_3_2_1_20_1","volume-title":"Smith","author":"Verma Prateek","year":"2018","unstructured":"Prateek Verma and Julius O . Smith . 2018 . Neural Style Transfer for Audio Spectograms . arXiv:arXiv:1801.01589 Prateek Verma and Julius O. Smith. 2018. Neural Style Transfer for Audio Spectograms. arXiv:arXiv:1801.01589"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"W. Xiong L. Wu F. Alleva J. Droppo X. Huang and A. Stolcke. 2017. The Microsoft 2017 Conversational Speech Recognition System. arXiv:arXiv:1708.06073  W. Xiong L. Wu F. Alleva J. Droppo X. Huang and A. Stolcke. 2017. The Microsoft 2017 Conversational Speech Recognition System. arXiv:arXiv:1708.06073","DOI":"10.1109\/ICASSP.2017.7953159"}],"event":{"name":"iiWAS2019: The 21st International Conference on Information Integration and Web-based Applications & Services","location":"Munich Germany","acronym":"iiWAS2019","sponsor":["JKU Johannes Kepler Universit\u00e4t Linz","@WAS International Organization of Information Integration and Web-based Applications and Services"]},"container-title":["Proceedings of the 21st International Conference on Information Integration and Web-based Applications & Services"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366030.3366083","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366030.3366083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:50Z","timestamp":1750202630000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366030.3366083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,2]]},"references-count":21,"alternative-id":["10.1145\/3366030.3366083","10.1145\/3366030"],"URL":"https:\/\/doi.org\/10.1145\/3366030.3366083","relation":{},"subject":[],"published":{"date-parts":[[2019,12,2]]},"assertion":[{"value":"2020-02-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}