基于多任务和对抗学习的鲁棒口吃检测
Robust Stuttering Detection via Multi-task and Adversarial Learning
摘要:
通过自动检测和识别口吃,言语病理学家可以跟踪口吃者(PWS)的不流利进展。在本文中,我们研究了多任务(MTL)和对抗学习(ADV)对学习鲁棒口吃特征的影响。这是首次将MTL和ADV用于口吃识别的初步研究。我们在SEP-28 k口吃数据集上评估了我们的系统,该数据集由来自385个播客的20小时(约)数据组成。我们的方法显示出有希望的结果,并在各种不流利类的基线。我们实现了高达10%,6.78%和2%的重复,块,和感叹词分别比基线的改善。
英文摘要:
By automatic detection and identification of stuttering, speech pathologists can track the progression of disfluencies of persons who stutter (PWS). In this paper, we investigate the impact of multi-task (MTL) and adversarial learning (ADV) to learn robust stutter features. This is the first-ever preliminary study where MTL and ADV have been employed in stuttering identification (SI). We evaluate our system on the SEP-28k stuttering dataset consisting of 20 hours (approx) of data from 385 podcasts. Our methods show promising results and outperform the baseline in various disfluency classes. We achieve up to 10%, 6.78%, and 2% improvement in repetitions, blocks, and interjections respectively over the baseline.
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。