Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment [article]

Yuan Gong, Ziyi Chen, Iek-Heng Chu, Peng Chang, James Glass
2022 arXiv   pre-print
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
more » ... 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.
arXiv:2205.03432v1 fatcat:jjj7grjgbjalzh62fg3fpyyare