1. Tone Recognition With Fractionized Models and Outlined Features Ye Tian, Jian-Lai Zhou, Min Chu, Eric Chang ICASSP 2004 Hsiao-Tsung Hung Department of Computer Science and Information Engineering National Taiwan Normal University

2. Outline Introduction Features – Detailed features – Outlined features – Experiments and analysis Tone Modeling – Experiments and analysis Conclusions

3. Introduction 2 questions 1.Is the detailed information of F0 curve useful for tone discrimination in continuous speech? 2.Are phoneme-independent tone models sufficient for continuous speech recognition?

4. Detailed features

5. Outlined features To reduce the number of parameters and improve the robustness. 1.Curve fitting features 2.Subsection Outlined features

6. Curve fitting features

7. Subsection Outlined features

8. Y X F0

9. Subsection Outlined features

13. Experiments and analysis 1.Main value and direction are the most important characteristics. 2.Detailed information is useless for tone discrimination.

14. Tone Modeling 1.One-tone-one-model tone models(5) 2.Monophone-dependent tone models(54) The same tone in different tonal phonemes is different modeled. 3.Triphone-dependent tone models(12824)

15. Experiments and analysis

16. Conclusions Using fractionized models and outlined features for tone recognition. Outlined features can reduce the interference caused by co-articulation effect, syllable stress, and sentence intonation.