用图结构处理发音歧义，提升语音识别准确率
Graph Connectionist Temporal Classification for Phoneme Recognition
- 构建发音序列图，让模型同时学习多个可能的发音
- 在英荷语数据上，错误率降低12.3%以上
- 适合用有噪声标注的语音识别系统优化
自动语音识别系统常使用文本通过音形转换（G2P）生成伪音素级标注进行训练。但G2P系统对每个词常输出多个可能发音，而标准连接时序分类（CTC）损失无法处理这种不确定性。本文将图时序分类（GTC）引入语音识别场景，使模型能基于包含多个发音路径的图结构进行训练，从而同时考虑每词的多种发音作为有效监督。在英语和荷兰语数据集上的实验表明，相比仅使用单一发音的基线模型，该方法持续降低音素错误率。结果表明，将发音变体纳入损失函数是利用嘈杂G2P标注训练语音识别系统的一种有效策略。
原文摘要 · Abstract (English)
Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per word, but the standard Connectionist Temporal Classification (CTC) loss cannot account for such ambiguity during training. In this work, we adapt Graph Temporal Classification (GTC) to the APR setting. GTC enables training from a graph of alternative phoneme sequences, allowing the model to consider multiple pronunciations per word as valid supervision. Our experiments on English and Dutch data sets show that incorporating multiple pronunciations per word into the training loss consistently improves phoneme error rates compared to a baseline trained with CTC. These results suggest that integrating pronunciation variation into the loss function is a promising strategy for training APR systems from noisy G2P-based supervision.
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。