用相似度检测边界，再聚类，轻松实现无监督词分割
Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
- 通过相邻特征差异预测词边界，避免复杂动态规划
- 在五种语言上达到顶尖效果，速度提升近5倍
- 适合追求高效无监督语音分析的研究者
本文研究无标签语音的词级分割与词汇聚类问题。传统方法依赖评分模型结合动态规划寻找最优分段，本文提出更简单的策略：利用相邻自监督特征的差异性预测词边界，再对预测段落进行聚类构建词典。为公平比较，我们改进了旧版ES-KMeans动态规划方法，采用更优特征与边界约束。在五语言ZeroSpeech基准测试中，该方法取得与最新ES-KMeans+相当的顶尖性能，同时速度接近提升5倍。
原文摘要 · Abstract (English)
We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation. Here we propose a much simpler strategy: we predict word boundaries using the dissimilarity between adjacent self-supervised features, then we cluster the predicted segments to construct a lexicon. For a fair comparison, we update the older ES-KMeans dynamic programming method with better features and boundary constraints. On the five-language ZeroSpeech benchmarks, our simple approach gives similar state-of-the-art results compared to the new ES-KMeans+ method, while being almost five times faster. Project webpage: https://s-malan.github.io/prom-seg-clus.
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。