MMSD-Net: Towards Multi-modal Stuttering Detection
This addresses the challenge of building efficient, context-aware speech processing systems for over 70 million people affected by stuttering, representing an incremental advance by adding visual modality to detection.
The paper tackles the problem of automatic stuttering detection by proposing MMSD-Net, the first multi-modal neural framework that incorporates visual signals, resulting in a 2-17% improvement in F1-score over existing uni-modal methods.
Stuttering is a common speech impediment that is caused by irregular disruptions in speech production, affecting over 70 million people across the world. Standard automatic speech processing tools do not take speech ailments into account and are thereby not able to generate meaningful results when presented with stuttered speech as input. The automatic detection of stuttering is an integral step towards building efficient, context-aware speech processing systems. While previous approaches explore both statistical and neural approaches for stuttering detection, all of these methods are uni-modal in nature. This paper presents MMSD-Net, the first multi-modal neural framework for stuttering detection. Experiments and results demonstrate that incorporating the visual signal significantly aids stuttering detection, and our model yields an improvement of 2-17% in the F1-score over existing state-of-the-art uni-modal approaches.