A transfer learning based approach for pronunciation scoring
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{sancinetti2022transfer,
author = {Marcelo Sancinetti and Jazmín Vidal and Cyntia Bonomi and Luciana Ferrer},
title = {{A transfer learning based approach for pronunciation scoring}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2022},
url = {https://openreview.net/forum?id=m45WGyF56p},
}Loading related content...