# Senone-aware Adversarial Multi-task Training for Unsupervised Child to Adult Speech Adaptation

arXiv: https://arxiv.org/abs/2102.11488 · HTML: https://mlsanity.com/paper/2102.11488/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 25 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 4 of 4)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [Speaker-Invariant Training via Adversarial Learning](https://mlsanity.com/paper/1804.00732/) (2018)
- [Non-native children speech recognition through transfer learning](https://mlsanity.com/paper/1809.09658/) (2018)

## Built on by (most cited first, 1 of 1)

- [Examining Test-Time Adaptation for Personalized Child Speech Recognition](https://mlsanity.com/paper/2409.13095/) (2024)

## Abstract (arXiv)

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.