Large Language Models for Dysfluency Detection in Stuttered Speech
This work addresses the need for more inclusive speech and language technologies by improving dysfluency detection, though it is incremental as it applies existing LLM methods to a specific domain.
The paper tackled the problem of detecting dysfluencies in stuttered speech by using large language models (LLMs) to combine acoustic and lexical information, achieving competitive results on multi-label detection tasks across English and German datasets.
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.