研究人员开发了两种自动标注语音转录错误的新方法。一种方法是语音翻译错误标注（STEL），它使用现有的仅文本和多模态大语言模型来识别语音翻译中的错误，尽管目前系统的精确度约为人类的一半。另一种方法是TalkTag，它采用经过微调的大语言模型来自动标注口语转录中的细粒度词句法错误，即使在数据有限的情况下也证明是有效的。 AI
影响 自动标注语音和转录中的错误可以加速自然语言处理和临床语言学领域的研究与开发。
排序理由 该集群包含两篇学术论文，描述了语音和转录中错误标注的新方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2606.06047v1 Announce Type: new Abstract: Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no established methodology for evaluating confidence and quality estimation of speech …
Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no established methodology for evaluating confidence and quality estimation of speech translations. To initiate progress in this direc…
arXiv:2606.01820v1 Announce Type: new Abstract: Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine…
Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation i…
Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation i…