利用wav2vec 2.0检测口吃治疗中的言语不流畅
Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0
AI总结：
本文利用wav2vec 2.0和多任务学习，通过微调检测口吃治疗中的言语不流畅性，提升分类性能达27%
摘要：
口吃是一种多样的言语障碍，会损害个体的沟通能力。口吃者（PWS）常常通过言语治疗来应对这种状况。改进针对此类非典型言语的语音识别系统或跟踪言语治疗的效果，需要能够检测不流畅性的同时也能检测治疗中获得的言语技巧的系统。本文表明，对包含不流畅语音的大型英语语料库上的wav2vec 2.0进行微调，结合多任务学习，可以提高通用wav2vec 2.0特征在检测语音不流畅性方面的效果；这在不同语言中都适用。我们通过训练支持向量机分类器，使用从微调模型中提取的特征，在六个不同的口吃相关事件类型上评估了我们的方法：块、延长、声音重复、词重复、感叹词以及特定于治疗的言语修改。使用微调模型的嵌入会导致相对分类性能提升高达27%（相对于F1分数）
英文摘要：
Stuttering is a varied speech disorder that harms an individual's communication ability. Persons who stutter (PWS) often use speech therapy to cope with their condition. Improving speech recognition systems for people with such non-typical speech or tracking the effectiveness of speech therapy would require systems that can detect dysfluencies while at the same time being able to detect speech techniques acquired in therapy. This paper shows that fine-tuning wav2vec 2.0 [1] for the classification of stuttering on a sizeable English corpus containing stuttered speech, in conjunction with multi-task learning, boosts the effectiveness of the general-purpose wav2vec 2.0 features for detecting stuttering in speech; both within and across languages. We evaluate our method on FluencyBank , [2] and the German therapy-centric Kassel State of Fluency (KSoF) [3] dataset by training Support Vector Machine classifiers using features extracted from the finetuned models for six different stuttering-related event types: blocks, prolongations, sound repetitions, word repetitions, interjections, and - specific to therapy - speech modifications. Using embeddings from the fine-tuned models leads to relative classification performance gains up to 27% w.r.t. F1-score.
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。
