Presentation | 2000/5/19 Automatic Estimation of Pronunciation Habits Using a Single Word Utterance Based upon a Stressed Syllable Detection Technique Nobuaki MINEMATSU, Seiichi NAKAGAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | More and more efforts have been recently made to apply speech technologies to language learning, especially to pronunciation learning. The authors have been focusing on Japanese manners of generating English word stress. This is because the pronunciation habits which are peculiar and inevitable to Japanese learners can be easily found in their stress generation manners. It is reported that Japanese learners tend to generate the English word stress mainly by controlling F_0, which is the very manner of producing the word accent of the Japanese language. And a stressed syllable detector, a pronunciation habit estimator, and a visualizer of the habit were developed in our previous study, where the estimated and visualized habits of the individual learners accorded quite well with their English pronunciation proficiency rated by four English teachers. However, the habit could be obtained only after a learner pronounced several dozens of words because the habit estimator referred to the rates of detecting the stressed syllables. In this paper, using another criterion, a method of the instantaneous estimation was proposed which required only a single word utterance. And it enables the interactive feedback to the learners. Results showed the high correlation between an average pattern of the instantaneously estimated habits and its corresponding habit obtained in our previous study. Furthermore, simplified methods of the instantaneous estimation were also investigated in this paper. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Word stress / Pronunciation habit / Stressed syllable detection / HMM / English CAI / Triangular representation |
Paper # | SP2000-2 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2000/5/19(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Speech (SP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Automatic Estimation of Pronunciation Habits Using a Single Word Utterance Based upon a Stressed Syllable Detection Technique |
Sub Title (in English) | |
Keyword(1) | Word stress |
Keyword(2) | Pronunciation habit |
Keyword(3) | Stressed syllable detection |
Keyword(4) | HMM |
Keyword(5) | English CAI |
Keyword(6) | Triangular representation |
1st Author's Name | Nobuaki MINEMATSU |
1st Author's Affiliation | School of Engineering, University of Tokyo() |
2nd Author's Name | Seiichi NAKAGAWA |
2nd Author's Affiliation | Dept.of Information and Computer Sciences, Toyohashi Univ.of Technology |
Date | 2000/5/19 |
Paper # | SP2000-2 |
Volume (vol) | vol.100 |
Number (no) | 97 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |