Large Language Models for Dysfluency Detection in Stuttered Speech

TL;DR

This paper explores using large language models combined with acoustic features to detect multiple types of dysfluencies in stuttered speech, aiming to improve inclusivity in speech technology.

Contribution

It introduces a novel approach that integrates acoustic and lexical data into LLMs for multi-label dysfluency detection, demonstrating competitive results.

Findings

Effective combination of acoustic and lexical information.

Achieved competitive results on three datasets.

Supports multi-label dysfluency detection.

Abstract

Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components and support the development of more inclusive speech and language technologies. Inspired by the recent trend towards the deployment of large language models (LLMs) as universal learners and processors of non-lexical inputs, such as audio and video, we approach the task of multi-label dysfluency detection as a language modeling problem. We present hypotheses candidates generated with an automatic speech recognition system and acoustic representations extracted from an audio encoder model to an LLM, and finetune the system to predict dysfluency labels on three datasets containing English and German stuttered speech. The experimental results show that our system effectively combines acoustic and lexical information and achieves competitive results on the multi-label stuttering detection task.