| Paper ID | HLT-15.5 |
| Paper Title |
SENONE-AWARE ADVERSARIAL MULTI-TASK TRAINING FOR UNSUPERVISED CHILD TO ADULT SPEECH ADAPTATION |
| Authors |
Richeng Duan, Nancy Chen, Agency for Science, Technology and Research (A*STAR), Singapore |
| Session | HLT-15: Language Assessment |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation |
Poster
|
| Topic |
Human Language Technology: [HLT-LACL] Language Acquisition and Learning |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Acoustic modeling for child speech is challenging due to the high acoustic variability caused by physiological differences in the vocal tract. The dearth of publicly available datasets makes the task more challenging. In this work, we propose a feature adaptation approach by exploiting adversarial multi-task training to minimize acoustic mismatch at the senone (tied triphone states) level between adult and child speech and leverage large amounts of transcribed adult speech. We validate the proposed method on three tasks: child speech recognition, child pronunciation assessment and child fluency score prediction. Empirical results indicate that our proposed approach consistently outperforms competitive baselines, achieving 7.7% relative error reduction on speech recognition and up to 25.2% relative gains on the evaluation tasks. |
