Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or in-domain language models, while the pronunciation aspect is seldom touched upon. This paper applies a novel computational analysis on the pronunciation variances in sung utterances and further proposes a new pronunciation model adapted for singing. The singing-adapted model is tested on multiple public datasets via word recognition experiments. It performs better than the standard speech dictionary in all settings reporting the best results on ALT in a capella recordings using n-gram language models. For reproducibility, we share the sentence-level annotations used in testing, providing a new benchmark evaluation set for ALT.

中文翻译：

---

宋词中的计算发音分析

最近的自动歌词转录 (ALT) 方法侧重于构建更强大的声学模型或域内语言模型，而很少涉及发音方面。本文对歌唱话语中的发音差异进行了新的计算分析，并进一步提出了一种适用于歌唱的新发音模型。通过单词识别实验在多个公共数据集上测试了适应唱歌的模型。它在使用 n-gram 语言模型的无伴奏合唱记录中报告 ALT 的最佳结果的所有设置中的性能都优于标准语音词典。为了可重复性，我们共享了测试中使用的句子级注释，为 ALT 提供了新的基准评估集。