论文标题
基于变形金刚的多范围的多个非母语英语的人发音评估
Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment
论文作者
论文摘要
自动发音评估是帮助自我指导的语言学习者的重要技术。虽然发音质量具有多个方面，包括准确性，流利性，完整性和韵律，但以前的努力通常仅在一个粒度（例如，在音素级别上）对一个方面（例如准确性）建模。在这项工作中，我们探讨了在多个粒度上进行多光值发音评估的建模。具体而言，我们通过多任务学习训练基于发音功能的变压器（GOPT）的优点。实验表明，GOPT通过在LibrisPeech上训练的公共自动语音识别（ASR）声学模型，在Speechocean762上取得了最佳结果。
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.
