# A transfer learning based approach for pronunciation scoring

arXiv: https://arxiv.org/abs/2111.00976 · HTML: https://mlsanity.com/paper/2111.00976/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 29 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 2 of 2)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Context-aware Goodness of Pronunciation for Computer-Assisted Pronunciation Training](https://mlsanity.com/paper/2008.08647/) (2020)

## Built on by (most cited first, 5 of 5)

- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Automatic Pronunciation Assessment -- A Review](https://mlsanity.com/paper/2310.13974/) (2023)
- [Score-balanced Loss for Multi-aspect Pronunciation Assessment](https://mlsanity.com/paper/2305.16664/) (2023)
- [Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment](https://mlsanity.com/paper/2406.15723/) (2024)
- [Mispronunciation detection using self-supervised speech representations](https://mlsanity.com/paper/2307.16324/) (2023)

## Abstract (arXiv)

Phone-level pronunciation scoring is a challenging task, with performance far from that of human annotators. Standard systems generate a score for each phone in a phrase using models trained for automatic speech recognition (ASR) with native data only. Better performance has been shown when using systems that are trained specifically for the task using non-native data. Yet, such systems face the challenge that datasets labelled for this task are scarce and usually small. In this paper, we present a transfer learning-based approach that leverages a model trained for ASR, adapting it for the task of pronunciation scoring. We analyze the effect of several design choices and compare the performance with a state-of-the-art goodness of pronunciation (GOP) system. Our final system is 20% better than the GOP system on EpaDB, a database for pronunciation scoring research, for a cost function that prioritizes low rates of unnecessary corrections.