{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:08:17Z","timestamp":1776121697963,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T00:00:00Z","timestamp":1587427200000},"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":[[2020,4,21]]},"DOI":"10.1145\/3313831.3376322","type":"proceedings-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T13:14:48Z","timestamp":1590585288000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["WithYou: Automated Adaptive Speech Tutoring With Context-Dependent Speech Recognition"],"prefix":"10.1145","author":[{"given":"Xinlei","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Miyaki","sequence":"additional","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Rekimoto","sequence":"additional","affiliation":[{"name":"University of Tokyo & Sony Computer Science Laboratories, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,4,23]]},"reference":[{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0266078412000223"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1515\/text-2014-0018"},{"key":"e_1_3_2_2_4_1","unstructured":"Dale-Chall Readability Test 2018. Dale-Chall Readability Formula with Word List. (2018). http:\/\/www.readabilityformulas.com\/free-dale-challtest.php."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.03.002"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Rodolfo Delmonte. 2011. Exploring speech technologies for language learning. In Speech and Language Technologies. InTech.","DOI":"10.5772\/16577"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/tesj.353"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-239"},{"key":"e_1_3_2_2_9_1","unstructured":"Farzad Ehsani and Eva Knodt. 1998. Speech technology in computer-aided language learning: Strengths and limitations of a new CALL paradigm. (1998)."},{"key":"e_1_3_2_2_10_1","unstructured":"ELSA. 2018. ELSA - Speak English fluently easily confidently. https:\/\/elsaspeak.com\/home. (2018)."},{"key":"e_1_3_2_2_11_1","unstructured":"Maxine Eskenazi. 1999. Using automatic speech processing for foreign language pronunciation tutoring: Some issues and a prototype. (1999)."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings INSTiL2000","volume":"1","author":"Eskenazi Maxine","year":"2000","unstructured":"Maxine Eskenazi, Yan Ke, Jordi Albornoz, and Katharina Probst. 2000. The fluency pronunciation trainer: Update and user issues. In Proceedings INSTiL2000, Vol. 1."},{"key":"e_1_3_2_2_13_1","unstructured":"Educational Testing Service (ETS). 2017. Test and score data summary for TOEFL iBT and PBT tests: January2017--December 2017 test data. (2017)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1075\/jslp.3.1.02foo"},{"key":"e_1_3_2_2_15_1","volume-title":"Bots as language learning tools. Language Learning & Technology","author":"Fryer LK","year":"2006","unstructured":"LK Fryer and Rollo Carpenter. 2006. Bots as language learning tools. Language Learning & Technology (2006)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.35307\/saltel.v2i2.35"},{"key":"e_1_3_2_2_17_1","unstructured":"C Ray Graham Deryle Lonsdale Casey Kennington Aaron Johnson and Jeremiah McGhee. 2008. Elicited Imitation as an Oral Proficiency Measure with ASR Scoring.. In LREC."},{"key":"e_1_3_2_2_18_1","volume-title":"Teaching EFL Learners Shadowing for Listening: Developing learners' bottom-up skills","author":"Hamada Yo","unstructured":"Yo Hamada. 2016a. Teaching EFL Learners Shadowing for Listening: Developing learners' bottom-up skills. Routledge."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.37546\/JALTTLT40.1-3"},{"key":"e_1_3_2_2_20_1","volume-title":"International Symposium on Automatic Detection of Errors in Pronunciation Training (IS ADEPT). 21--30","author":"H\u00f6nig Florian","year":"2012","unstructured":"Florian H\u00f6nig, Anton Batliner, and Elmar N\u00f6th. 2012. Automatic assessment of non-native prosody annotation, modelling and evaluation. In International Symposium on Automatic Detection of Errors in Pronunciation Training (IS ADEPT). 21--30."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2009-11"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2010-69"},{"key":"e_1_3_2_2_23_1","first-page":"43","article-title":"A preliminary study of applying shadowing technique to English intonation instruction","volume":"11","author":"Hsieh Kun-Ting","year":"2013","unstructured":"Kun-Ting Hsieh, Da-Hui Dong, and Li-Yi Wang. 2013. A preliminary study of applying shadowing technique to English intonation instruction. Taiwan Journal of Linguistics 11, 2 (2013), 43--65.","journal-title":"Taiwan Journal of Linguistics"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Wenping Hu Yao Qian and Frank K Soong. 2013. A new DNN-based high quality pronunciation evaluation for computer-aided language learning (CALL).. In Interspeech. 1886--1890.","DOI":"10.21437\/Interspeech.2013-458"},{"key":"e_1_3_2_2_25_1","unstructured":"Wenping Hu Yao Qian and Frank K Soong. 2015. An improved DNN-based approach to mispronunciation detection and diagnosis of L2 learners' speech.. In SLaTE. 71--76."},{"key":"e_1_3_2_2_26_1","volume-title":"Hansj\u00f6rg Mixdorff, Hongwei Ding, Qianyong Gao, Guoping Hue, Si Wei, and Zhao Chao.","author":"Hussein Hussein","year":"2011","unstructured":"Hussein Hussein, Hue San Do, Hansj\u00f6rg Mixdorff, Hongwei Ding, Qianyong Gao, Guoping Hue, Si Wei, and Zhao Chao. 2011. Mandarin tone perception and production by German learners. In Speech and Language Technology in Education."},{"key":"e_1_3_2_2_27_1","volume-title":"Society for Information Technology & Teacher Education International Conference. Association for the Advancement of Computing in Education (AACE), 1201--1207","author":"Jia Jiyou","year":"2004","unstructured":"Jiyou Jia. 2004. The study of the application of a web-based chatbot system on the teaching of foreign languages. In Society for Information Technology & Teacher Education International Conference. Association for the Advancement of Computing in Education (AACE), 1201--1207."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2008.09.001"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-230"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7967(67)90023-X"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference. Asia-Pacific Signal and Information Processing Association","author":"Lee Akinobu","year":"2009","unstructured":"Akinobu Lee and Tatsuya Kawahara. 2009. Recent development of open-source speech recognition engine julius. In Proceedings: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference. Asia-Pacific Signal and Information Processing Association, 2009 Annual ..., 131--137."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Ju Lin Yanlu Xie and Jinsong Zhang. 2016. Automatic Pronunciation Evaluation of Non-Native Mandarin Tone by Using Multi-Level Confidence Measures.. In INTERSPEECH. 2666--2670.","DOI":"10.21437\/Interspeech.2016-1162"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-476"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118894.1118898"},{"key":"e_1_3_2_2_35_1","volume-title":"Working memory and second language accent acquisition. Applied Cognitive Psychology","author":"Mattys Sven L","year":"2019","unstructured":"Sven L Mattys and Alan Baddeley. 2019. Working memory and second language accent acquisition. Applied Cognitive Psychology (2019)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2009-16"},{"key":"e_1_3_2_2_37_1","unstructured":"Jack Mostow and others. 2001. Evaluating tutors that listen: An overview of Project LISTEN. (2001)."},{"key":"e_1_3_2_2_38_1","unstructured":"NASA-TLX 2018. The Official NASA Task Load Index (TLX). (2018). https:\/\/humansystems.arc.nasa.gov\/groups\/TLX\/."},{"key":"e_1_3_2_2_39_1","article-title":"Using'A Shadowing'Technique'to Improve English Pronunciation Deficient Adult Japanese Learners: An Action Research on Expatriate Japanese Adult Learners","volume":"7","author":"Omar Hamzah Md","year":"2010","unstructured":"Hamzah Md Omar and Miko Umehara. 2010. Using'A Shadowing'Technique'to Improve English Pronunciation Deficient Adult Japanese Learners: An Action Research on Expatriate Japanese Adult Learners. Journal of Asia TEFL 7, 2 (2010).","journal-title":"Journal of Asia TEFL"},{"key":"e_1_3_2_2_40_1","first-page":"81","article-title":"Exploring differences between shadowing and repeating practices: An analysis of reproduction rate and types of reproduced words","volume":"21","author":"Shiki Osato","year":"2010","unstructured":"Osato Shiki, Yoko MORI, Shuhei KADOTA, and Shinsuke YOSHIDA. 2010. Exploring differences between shadowing and repeating practices: An analysis of reproduction rate and types of reproduced words. ARELE: Annual Review of English Language Education in Japan 21 (2010), 81--90.","journal-title":"ARELE: Annual Review of English Language Education in Japan"},{"key":"e_1_3_2_2_41_1","unstructured":"U.S.DEPARTMENT OF STATE. 2018. FSI's Experience with Language Learning. https:\/\/www.state.gov\/m\/fsi\/sls\/c78549.htm. (2018)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2375572"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.56040\/hdsm1611"},{"key":"e_1_3_2_2_44_1","volume-title":"Shadoingu to ondoku to eigoshutoku no kagaku.[Science of shadowing, oral reading, and English acquisition]","author":"Syuhei Kadota","unstructured":"Kadota Syuhei. 2012. Shadoingu to ondoku to eigoshutoku no kagaku.[Science of shadowing, oral reading, and English acquisition]. Tokyo: Cosmopier."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2449396.2449398"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.03.006"},{"key":"e_1_3_2_2_47_1","volume-title":"Filled pauses as cues to the complexity of upcoming phrases for native and non-native listeners. Speech communication 50, 2","author":"Watanabe Michiko","year":"2008","unstructured":"Michiko Watanabe, Keikichi Hirose, Yasuharu Den, and Nobuaki Minematsu. 2008. Filled pauses as cues to the complexity of upcoming phrases for native and non-native listeners. Speech communication 50, 2 (2008), 81--94."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1080\/0958822950080403"},{"key":"e_1_3_2_2_50_1","volume-title":"Phone-level pronunciation scoring and assessment for interactive language learning. Speech communication 30, 2--3","author":"Witt Silke M","year":"2000","unstructured":"Silke M Witt and Steve J Young. 2000. Phone-level pronunciation scoring and assessment for interactive language learning. Speech communication 30, 2--3 (2000), 95--108."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.29333\/iji.2019.12156a"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-728"}],"event":{"name":"CHI '20: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '20","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3313831.3376322","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3313831.3376322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:32:56Z","timestamp":1750199576000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3313831.3376322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,21]]},"references-count":50,"alternative-id":["10.1145\/3313831.3376322","10.1145\/3313831"],"URL":"https:\/\/doi.org\/10.1145\/3313831.3376322","relation":{},"subject":[],"published":{"date-parts":[[2020,4,21]]},"assertion":[{"value":"2020-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}