无需词典即可准确检测语音识别中的词边界。
Target word activity detector: An approach to obtain ASR word boundaries without lexicon
- 利用子词单元的词嵌入和预训练模型推断词边界。
- 在五种语言上验证，性能优于强基线。
- 支持多语言扩展，无额外计算开销。
端到端语音识别模型缺乏训练时的显式时间对齐，导致获取词级时间戳仍具挑战性，尤其在多语言场景下更为复杂。现有方法或依赖词典，或引入额外标记，存在可扩展性差与计算成本高的问题。本文提出一种新方法，不依赖词典即可估计词边界。该方法基于子词单元的词嵌入与预训练的语音识别模型，仅需训练阶段的词对齐信息。所提方法可无缝扩展至任意数量语言，且不增加额外开销。我们在一个包含五种语言的多语言语音识别模型上验证了该方法，结果表明其在性能上显著优于强基线。
原文摘要 · Abstract (English)
Obtaining word timestamp information from end-to-end (E2E) ASR models remains challenging due to the lack of explicit time alignment during training. This issue is further complicated in multilingual models. Existing methods, either rely on lexicons or introduce additional tokens, leading to scalability issues and increased computational costs. In this work, we propose a new approach to estimate word boundaries without relying on lexicons. Our method leverages word embeddings from sub-word token units and a pretrained ASR model, requiring only word alignment information during training. Our proposed method can scale-up to any number of languages without incurring any additional cost. We validate our approach using a multilingual ASR model trained on five languages and demonstrate its effectiveness against a strong baseline.
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。