Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment
Abstract
Automatic pronunciation assessment is an important technology to help self-directed language learners. While pronunciation quality has multiple aspects including accuracy, fluency, completeness, and prosody, previous efforts typically only model one aspect (e.g., accuracy) at one granularity (e.g., at the phoneme-level). In this work, we explore modeling multi-aspect pronunciation assessment at multiple granularities. Specifically, we train a Goodness Of Pronunciation feature-based Transformer (GOPT) with multi-task learning. Experiments show that GOPT achieves the best results on speechocean762 with a public automatic speech recognition (ASR) acoustic model trained on Librispeech.
Cite
@article{arxiv.2205.03432,
title = {Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment},
author = {Yuan Gong and Ziyi Chen and Iek-Heng Chu and Peng Chang and James Glass},
journal= {arXiv preprint arXiv:2205.03432},
year = {2022}
}
Comments
Accepted at ICASSP 2022. Code at https://github.com/YuanGongND/gopt Interactive Colab demo at https://colab.research.google.com/github/YuanGongND/gopt/blob/master/colab/GOPT_GPU.ipynb . ICASSP 2022