仅用母语数据实现轻量级发音评估，无需大量标注
Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal
- 用自监督编码器和聚类将语音转为离散符号，计算音位偏离度
- 引入文本引导的对齐模块，使评估结果相关性提升至PCC 0.66
- 适合资源有限场景，尤其适合无标注或少标注的发音评估
自动化发音评估通常依赖于标注的错误数据或非母语语料库，成本较高。本文提出一种仅使用母语资源训练的轻量级框架，可在无监督或少量评分语句校准下运行。推理时，学习者语音通过自监督编码器与K均值码本离散化，基于母语序列训练的词元语言模型计算符号惊喜度，惊喜度越高表示音位结构偏离越大。进一步引入文本引导的Text2DUnit--DTW模块，从参考文本预测母语词元序列并将其与声学词元对齐，生成误差敏感特征。惊喜度与对齐特征通过简单回归融合。在SpeechOcean762上，加入文本引导后皮尔逊相关系数（PCC）从0.60提升至0.66，接近有监督基线；在跨数据集测试中，L2-ARCTIC也表现出一致提升。
原文摘要 · Abstract (English)
Training automated pronunciation assessment often relies on labeled learner errors or non-native corpora that are costly to collect. We propose a lightweight framework trained only on native speech resources, operating unsupervised or lightly calibrated with a small set of scored utterances. At inference, learner speech is discretized with an SSL encoder and a K-means codebook. A token language model trained on native sequences computes surprisal where higher surprisal indicates phonotactic deviation. We add a transcript-guided Text2DUnit--DTW module that predicts native token sequences from reference text and aligns them to acoustic tokens to derive error-sensitive features. Surprisal and alignment features are fused via simple regression. On SpeechOcean762, PCC improves from 0.60 to 0.66 with transcript guidance, near supervised baselines. Cross-dataset evaluation on L2-ARCTIC shows consistent gains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。