# Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition

arXiv: https://arxiv.org/abs/2204.00819 · HTML: https://mlsanity.com/paper/2204.00819/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2022.

## Built on by (most cited first, 6 of 6)

- [Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition](https://mlsanity.com/paper/2307.05956/) (2023)
- [LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASR](https://mlsanity.com/paper/2309.16178/) (2023)
- [BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR](https://mlsanity.com/paper/2501.12602/) (2025)
- [Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation](https://mlsanity.com/paper/2205.07100/) (2022)
- [Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR](https://mlsanity.com/paper/2510.25150/) (2025)
- [You Sound a Little Tense: L2 Tailored Clear TTS Using Durational Vowel Properties](https://mlsanity.com/paper/2506.23367/) (2025)

## Abstract (arXiv)

In Uyghur speech, consonant and vowel reduction are often encountered, especially in spontaneous speech with high speech rate, which will cause a degradation of speech recognition performance. To solve this problem, we propose an effective phone mask training method for Conformer-based Uyghur end-to-end (E2E) speech recognition. The idea is to randomly mask off a certain percentage features of phones during model training, which simulates the above verbal phenomena and facilitates E2E model to learn more contextual information. According to experiments, the above issues can be greatly alleviated. In addition, deep investigations are carried out into different units in masking, which shows the effectiveness of our proposed masking unit. We also further study the masking method and optimize filling strategy of phone mask. Finally, compared with Conformer-based E2E baseline without mask training, our model demonstrates about 5.51% relative Word Error Rate (WER) reduction on reading speech and 12.92% on spontaneous speech, respectively. The above approach has also been verified on test-set of open-source data THUYG-20, which shows 20% relative improvements.