English(EN) Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming

新方法改进多语言词级语音对齐

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-09 10:27

研究人员开发了一种新颖的多语言词级强制对齐方法，集成了Massively Multilingual Speech (MMS) 模型中的表示和一个自监督音素边界检测器。该方法使用学习型动态规划解码器来推断精确的词边界。该系统在TIMIT和Buckeye数据集上与Montreal Forced Aligner (MFA) 等现有方法相比，表现出优越的性能，并在未见过（unseen）的语言上显示出有希望的结果，表明其可扩展性可覆盖MMS支持的1100多种语言。 AI

影响提高了多语言语音处理的准确性，可能改进跨语言AI应用。

排序理由该集群包含一篇详细介绍语音对齐新方法的学术论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Roy Weber, Meidan Zehavi, Rotem Rousso, Joseph Keshet · 2026-06-10 04:00

Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming

arXiv:2606.10675v1 Announce Type: new Abstract: We present a method for accurate multilingual word-level forced alignment, consisting of an alignment encoder and a learned alignment decoder. The encoder integrates two representations: one from the Massively Multilingual Speech (M…
arXiv cs.CL TIER_1 English(EN) · Joseph Keshet · 2026-06-09 10:27

Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming

We present a method for accurate multilingual word-level forced alignment, consisting of an alignment encoder and a learned alignment decoder. The encoder integrates two representations: one from the Massively Multilingual Speech (MMS) model and another from a self-supervised pho…

报道来源 [2]

Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming

Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming

相关实体

相关话题