{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:34:43Z","timestamp":1750221283483,"version":"3.41.0"},"publisher-location":"New York, New York, USA","reference-count":23,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1145\/3124116.3124119","type":"proceedings-article","created":{"date-parts":[[2017,9,13]],"date-time":"2017-09-13T16:20:10Z","timestamp":1505319610000},"page":"14-20","source":"Crossref","is-referenced-by-count":2,"title":["Speech interaction of educational robot based on Ekho and Sphinx"],"prefix":"10.1145","author":[{"given":"Zhenyu","family":"Li","sequence":"first","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinguo","family":"Yu","sequence":"additional","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Hu","sequence":"additional","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/3124116.3124119-1","doi-asserted-by":"crossref","unstructured":"Rudzicz, F., Wang, R., Begum, M., et al. 2015. Speech Interaction with Personal Assistive Robots Supporting Aging at Home for Individuals with Alzheimer's Disease. Acm Transactions on Accessible Computing, 7(2), 1--22.","DOI":"10.1145\/2744206"},{"key":"key-10.1145\/3124116.3124119-2","doi-asserted-by":"crossref","unstructured":"Chuah, M. C., Coombe, D., Garman, C., et al. 2014. Lehigh Instrument for Learning Interaction (LILI): An Interactive Robot to Aid Development of Social Skills for Autistic Children[C]. IEEE, International Conference on Mobile Ad Hoc and Sensor Systems. IEEE, 731--736.","DOI":"10.1109\/MASS.2014.67"},{"key":"key-10.1145\/3124116.3124119-3","doi-asserted-by":"crossref","unstructured":"Deng, L., Wang, K., and Wu, C. 2005. Speech technology and systems in human-machine communication [from the Guest Editors]. IEEE Signal Processing Magazine, 22(5), 12--14.","DOI":"10.1109\/MSP.2005.1511818"},{"key":"key-10.1145\/3124116.3124119-4","doi-asserted-by":"crossref","unstructured":"Burbules, N. C. 2000. Dialogue in Teaching: Theory and Practice, Journal of Curriculum Studies, 32(6), 878--881.","DOI":"10.1080\/00220270050167233"},{"key":"key-10.1145\/3124116.3124119-5","unstructured":"Khorinphan, C., Phansamdaeng, S., and Saiyod, S. 2014. Thai speech synthesis with emotional tone: Based on Formant synthesis for Home Robot. Third ICT International Student Project Conference (ICT-ISPC), I. IEEE, 111--114."},{"key":"key-10.1145\/3124116.3124119-6","unstructured":"Moulines, E. and Charpentier, F.. 1990. Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Communication, 9(5--6), 453--467."},{"key":"key-10.1145\/3124116.3124119-7","doi-asserted-by":"crossref","unstructured":"Tokuda, K., Nankaku, Y., Toda, T., et al. 2013.Speech Synthesis Based on Hidden Markov Models. Proceedings of the IEEE, 101(5), 1234--1252.","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"key-10.1145\/3124116.3124119-8","doi-asserted-by":"crossref","unstructured":"Ze, H., Senior, A., and Schuster, M. 2013. Statistical parametric speech synthesis using deep neural networks. IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 7962--7966.","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"key-10.1145\/3124116.3124119-9","doi-asserted-by":"crossref","unstructured":"Takamichi, S., Toda, T., Shiga, Y., et al. 2014. Parameter Generation Methods with Rich Context Models for High-Quality and Flexible Text-To-Speech Synthesis. IEEE Journal of Selected Topics in Signal Processing, 239--250.","DOI":"10.1109\/JSTSP.2013.2288599"},{"key":"key-10.1145\/3124116.3124119-10","unstructured":"Anusuya, M. A. and Katti, S. K. 2009. Speech Recognition by Machine: A Review. International Journal of Computer Science and Information Security, 64(4), 501--531."},{"key":"key-10.1145\/3124116.3124119-11","unstructured":"Hjulström, R. 2015. Evaluation of a speech recognition system Pocketsphinx. Umeå University, Sweden. http:\/\/urn.kb.se\/resolve?urn=urn:nbn:se:umu:diva-108293"},{"key":"key-10.1145\/3124116.3124119-12","unstructured":"Gales, M. and Young, S. 2008. The application of hidden Markov models in speech recognition. Foundations and Trends® in Signal Processing, 1(3), 195--304."},{"key":"key-10.1145\/3124116.3124119-13","doi-asserted-by":"crossref","unstructured":"Hinton, G., Deng, L., Yu, D., et al. 2012. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine, 29(6), 82--97.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"key-10.1145\/3124116.3124119-14","doi-asserted-by":"crossref","unstructured":"Lou, H. L. 1995. Implementing the Viterbi algorithm. Signal Processing Magazine, IEEE, 12(5), 42--52.","DOI":"10.1109\/79.410439"},{"key":"key-10.1145\/3124116.3124119-15","doi-asserted-by":"crossref","unstructured":"Liu, W. and Han, W. 2010. Improved Viterbi algorithm in continuous speech recognition. International Conference on Computer Application and System Modeling. IEEE, V7-207--V7-209.","DOI":"10.1109\/ICCASM.2010.5620406"},{"key":"key-10.1145\/3124116.3124119-16","unstructured":"Xiong, W., Droppo, J., Huang, X., et al. 2016. Achieving Human Parity in Conversational Speech Recognition. arXiv:1610.05 256v1 [cs.CL] 17 Oct 2016."},{"key":"key-10.1145\/3124116.3124119-17","unstructured":"Amodei, D., Anubhai, R., Battenberg, E., et al. 2015. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin. Computer Science."},{"key":"key-10.1145\/3124116.3124119-18","unstructured":"\"How to Install Ekho (for Linux and Raspberry Pi)\", http:\/\/www.eguidedog.net\/cn\/ekho_cn.php."},{"key":"key-10.1145\/3124116.3124119-19","doi-asserted-by":"crossref","unstructured":"Kai-Fu Lee, Hon, H. W., R Reddy. 1990. An Overview of the SPHINX Speech Recognition System. IEEE Transactions on Acoustics Speech, and Signal Processing. 38(1), 35--45.","DOI":"10.1109\/29.45616"},{"key":"key-10.1145\/3124116.3124119-20","unstructured":"Huggins-Daines, D., Kumar, M., Chan, A., et al. 2006. Pocketsphinx: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices. IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. IEEE, I-I."},{"key":"key-10.1145\/3124116.3124119-21","unstructured":"Chen, Stanley, F., Goodman, et al. 1999. An empirical study of smoothing techniques for language modeling. Computer Speech and Language, 13(4), 359--393."},{"key":"key-10.1145\/3124116.3124119-22","unstructured":"Ma, R., Yue, H., Gao, Q., et al. 2007. Research on Intelligent-Robot-Oriented Speech Interactive Technology and Module. IEEE International Conference on Control and Automation. IEEE, 1263--1267."},{"key":"key-10.1145\/3124116.3124119-23","unstructured":"Online reading of \"Ancient Poems of primary school\", http:\/\/www.gushiwen.org\/gushi\/xiaoxue.aspx."}],"event":{"name":"the 2017 International Conference","start":{"date-parts":[[2017,7,9]]},"number":"2017","location":"Singapore, Singapore","end":{"date-parts":[[2017,7,11]]},"acronym":"ICEMT '17"},"container-title":["Proceedings of the 2017 International Conference on Education and Multimedia Technology  - ICEMT '17"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3124116.3124119","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=3124119&ftid=1905929&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:22Z","timestamp":1750212682000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=3124116.3124119"}},"subtitle":[],"proceedings-subject":"Education and Multimedia Technology","short-title":[],"issued":{"date-parts":[[2017]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1145\/3124116.3124119","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}