# AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge

arXiv: https://arxiv.org/abs/2102.09828 · HTML: https://mlsanity.com/paper/2102.09828/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2021.

## Built on by (most cited first, 4 of 4)

- [CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice](https://mlsanity.com/paper/2305.18283/) (2023)
- [Modelling low-resource accents without accent-specific TTS frontend](https://mlsanity.com/paper/2301.04606/) (2023)
- [Low-resource speech recognition and dialect identification of Irish in a multi-task framework](https://mlsanity.com/paper/2405.01293/) (2024)
- [GE2E-AC: Generalized End-to-End Loss Training for Accent Classification](https://mlsanity.com/paper/2407.14021/) (2024)

## Abstract (arXiv)

This paper describes the AISpeech-SJTU system for the accent identification track of the Interspeech-2020 Accented English Speech Recognition Challenge. In this challenge track, only 160-hour accented English data collected from 8 countries and the auxiliary Librispeech dataset are provided for training. To build an accurate and robust accent identification system, we explore the whole system pipeline in detail. First, we introduce the ASR based phone posteriorgram (PPG) feature to accent identification and verify its efficacy. Then, a novel TTS based approach is carefully designed to augment the very limited accent training data for the first time. Finally, we propose the test time augmentation and embedding fusion schemes to further improve the system performance. Our final system is ranked first in the challenge and outperforms all the other participants by a large margin. The submitted system achieves 83.63% average accuracy on the challenge evaluation data, ahead of the others by more than 10% in absolute terms.