Abstract
Retroflex aspirates in Chinese are generally difficult for Japanese students learning pronunciation. In particular, discriminating between utterances of aspirated dental and retroflex syllables is the most difficult to learn. We extracted the features of correctly pronouncing the aspirated dental syllables ca[ʦ‘a], ci[ʦ‘i], and ce[ʦ‘ɤ] and aspirated retroflex ones cha[tʂ‘a], chi[tʂ‘i], and che[tʂ‘ɤ] by observing the spectrum evolution of breathing power during both voice onset time and voiced period of sounds uttered by nine Chinese native speakers. We developed a 35-channel filter bank on a personal computer to analyze the evolution of breathing power spectrum by using MATLAB. We then automatically evaluated the utterances of 20 students judged to be correct by native Chinese speakers and obtained a success rate of higher than 90% and 95% for aspirated retroflex and dental syllables, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hoshino, A., Yasuda, A.: Evaluation of Chinese aspiration sounds uttered by Japanese students using VOT and power. Acoust. Soc. Jpn. 58(11), 689–695 (2002) (in Japanese)
Hoshino, A., Yasuda, A.: The evaluation of Chinese aspiration sounds uttered by Japanese student using VOT and power. In: IEEE Proceedings of 2003 International Conference on Acoustics, Speech, and Signal Processing, Hong Kong, pp. 472–475 (2003)
Hoshino, A., Yasuda, A.: Dependence of correct pronunciation of Chinese aspirated sounds on power during voice onset time. In: Proceeding of ISCSLP 2004, Hong Kong, pp. 121–124 (2004)
Hoshino, A., Yasuda, A.: Effect of Japanese articulation of stops on pronunciation of Chinese aspirated sounds by Japanese students. In: Proceeding of ISCSLP 2004, Hong Kong, pp. 125–128 (2004)
Hoshino, A., Yasuda, A.: Evaluation of aspiration sound of Chinese labial and alveolar diphthong uttered by Japanese students using voice onset time and breathing power. In: Proceeding of ISCSLP 2006, Singapore, pp. 13–24 (2006)
Hoshino, A., Yasuda, A.: Pronunciation Training System for Japanese Students Learning Chinese Aspiration. In: The 2nd International Conference on Society and Information Technologies (ICSIT), Orlando, Florida, USA, pp. 288–293 (2011)
Hoshino, A., Yasuda, A.: Pronunciation Training System of Chinese Aspiration for Japanese Students. Acoustical Science and Technology 32(4), 154–157 (2011)
Hoshino, et al.: Acoustics 2012, Nantes, France, pp. 339–344 (April 2012)
Kent, R.D., Read, C.: The Acoustic Analysis of Speech, pp. 105–109. Singular Publishing Group, Inc., San Diego (1992)
Zhu, C.: Studying Method of the Pronunciation of Chinese Speech for Foreign Students, pp. 63–71. Yu Wu Publishing Co., China (1997) (in Chinese)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hoshino, A., Yasuda, A. (2013). Automatic Discrimination of Pronunciations of Chinese Retroflex and Dental Affricates. In: Sun, M., Zhang, M., Lin, D., Wang, H. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2013 2013. Lecture Notes in Computer Science(), vol 8202. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41491-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-41491-6_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41490-9
Online ISBN: 978-3-642-41491-6
eBook Packages: Computer ScienceComputer Science (R0)