Notes
- The L1 speaker speaks the General American Accent
- YKWK's native language is Korean
- TXHC's native language is Chinese
- Dataset (L2-ARCTIC corpus [1]): https://psi.engr.tamu.edu/l2-arctic-corpus/
Experiment : Evaluating the reference-free golden speakers
- Input speech: original unmodified L2 speech recordings
- Baseline: the reference-free FAC system of Zhao et al. [2]; samples provided through the courtesy of G. Zhao (TAMU)
- Proposed: the proposed reference-free accent conversion model
| L2 speaker | Text | Input speech | Reference-Free Accent conversion (Baseline) | Reference-Free Accent conversion (Proposed) |
|---|---|---|---|---|
| YKWK | He had fulfilled his duty and paid properly. | |||
| But already he had composed himself. | ||||
| The Russian music player, the Count, was her obedient slave. | ||||
| TXHC | What an excited whispering and conferring took place. | |||
| Thus he turned the tenets and jargon of psychology back on me. | ||||
| You were making them talk shop, Ruth charged him. |
References
[1] G. Zhao et al., "L2-ARCTIC: A non-native English speech corpus," in Proc. Interspeech, 2018, pp. 2783-2787.
[2] G. Zhao, S. Ding, and R. Gutierrez-Osuna., "Converting Foreign Accent Speech Without a Reference." IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, pp.2367-2381.