Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings

Studies show that persons who stutter (PWS) encounter several hardships in social and professional interactions (Kehoe and Contributors 2006). In addition, more people are progressively interacting with voice assistants, but they ignore and fail to recognize stuttered speech (Sheikh et al. 2021a), and the stuttering detection (SD) can be exploited to improve automatic speech recognition (ASR) for PWS to access voice assistants such as Alexa, Siri, etc. Usually, SD is addressed by various listening and brain scan tests (Ingham et al. 1996; Smith and Weber 2017; Sheikh et al. 2021a). However, this method of SD is high-priced and requires a demanding effort from speech therapists. The presence of uncontrolled utterances is reflected in the acoustic domain, which helps to discriminate them in various stuttering types. Based on the acoustic cues present in stuttered speech, several people employed a machine learning paradigm for SD. Some of the current state-of-the-art stuttering detection deep learning modelling techniques include: ResNet+BiLSTM (Kourkounakis et al. 2020; Jouaiti and Dautenhahn), FluentNet (Kourkounakis et al. 2021), StutterNet (Sheikh et al. 2021b, 2023).