StutterNet: Stuttering Detection Using Time Delay Neural Network

TL;DR

StutterNet is a deep learning model that detects and classifies stuttering disfluencies directly from acoustic signals using a time-delay neural network, outperforming existing methods that rely on speech recognition systems.

Contribution

This work introduces StutterNet, a TDNN-based approach that detects stuttering without relying on ASR, reducing complexity and improving performance.

Findings

Outperforms state-of-the-art residual neural network methods

Uses fewer trainable parameters due to parameter sharing

Achieves promising detection accuracy on UCLASS dataset

Abstract

This paper introduces StutterNet, a novel deep learning based stuttering detection capable of detecting and identifying various types of disfluencies. Most of the existing work in this domain uses automatic speech recognition (ASR) combined with language models for stuttering detection. Compared to the existing work, which depends on the ASR module, our method relies solely on the acoustic signal. We use a time-delay neural network (TDNN) suitable for capturing contextual aspects of the disfluent utterances. We evaluate our system on the UCLASS stuttering dataset consisting of more than 100 speakers. Our method achieves promising results and outperforms the state-of-the-art residual neural network based method. The number of trainable parameters of the proposed method is also substantially less due to the parameter sharing scheme of TDNN.