基于困难类别挖掘与类间焦点损失的填充词检测
Filler Word Detection with Hard Category Mining and Inter-Category Focal Loss
AI总结:
本文提出一种填充词检测方法,通过动态挖掘困难类别并引入类间焦点损失,有效区分填充词与易混淆词,在PodcastFillers数据集上取得显著提升。
摘要:
像“um”或“uh”这样的填充词在自发语音中很常见。由于它们会影响语音的流畅性、自信度和专业性,因此希望在录音中自动检测并去除它们。先前的研究和我们的初步实验表明,填充词检测的最大挑战在于填充词很容易与其他困难类别(如“a”或“I”)混淆。在本文中,我们提出了一种新颖的填充词检测方法,通过动态添加辅助类别并应用额外的类间焦点损失来有效应对这一挑战。辅助类别通过挖掘困难类别,迫使模型对易混淆词进行显式建模。此外,类间焦点损失自适应地调整“填充词”和“非填充词”类别之间的惩罚权重,以处理“非填充词”类别中剩余的其他易混淆词。我们的系统在PodcastFillers数据集上取得了最佳结果,与其他方法相比有显著提升。
英文摘要:
Filler words like ``um" or ``uh" are common in spontaneous speech. It is desirable to automatically detect and remove them in recordings, as they affect the fluency, confidence, and professionalism of speech. Previous studies and our preliminary experiments reveal that the biggest challenge in filler word detection is that fillers can be easily confused with other hard categories like ``a" or ``I". In this paper, we propose a novel filler word detection method that effectively addresses this challenge by adding auxiliary categories dynamically and applying an additional inter-category focal loss. The auxiliary categories force the model to explicitly model the confusing words by mining hard categories. In addition, inter-category focal loss adaptively adjusts the penalty weight between ``filler" and ``non-filler" categories to deal with other confusing words left in the ``non-filler" category. Our system achieves the best results, with a huge improvement compared to other methods on the PodcastFillers dataset.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。