Senone-Aware Adversarial Multi-Task Training for Unsupervised Child to Adult Speech Adaptation

• Published in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 7758 - 7762
• Main Authors: Duan, Richeng, Chen, Nancy F.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06-06-2021
• Subjects: Acoustics; Adaptation models; automatic speech evaluation; child speech recognition; Pediatrics; Signal processing; Speech recognition; Training; Transforms; unsupervised feature adaptation
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP39728.2021.9413738

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.