Towards a Method for Synthetic Generation of Persons with Aphasia Transcripts

TL;DR

This paper explores methods to generate synthetic aphasic speech transcripts using procedural programming and large language models, aiming to address data scarcity in aphasia research and improve automated recognition systems.

Contribution

It introduces two novel methods for synthetic transcript generation, leveraging LLMs and procedural techniques, validated across severity levels to better model aphasic speech patterns.

Findings

Mistral 7b Instruct best captures linguistic degradation

Synthetic transcripts show realistic changes in NDW, word count, and length

Methods can aid in creating larger datasets for aphasia research

Abstract

In aphasia research, Speech-Language Pathologists (SLPs) devote extensive time to manually coding speech samples using Correct Information Units (CIUs), a measure of how informative an individual sample of speech is. Developing automated systems to recognize aphasic language is limited by data scarcity. For example, only about 600 transcripts are available in AphasiaBank yet billions of tokens are used to train large language models (LLMs). In the broader field of machine learning (ML), researchers increasingly turn to synthetic data when such are sparse. Therefore, this study constructs and validates two methods to generate synthetic transcripts of the AphasiaBank Cat Rescue picture description task. One method leverages a procedural programming approach while the second uses Mistral 7b Instruct and Llama 3.1 8b Instruct LLMs. The methods generate transcripts across four severity levels (Mild, Moderate, Severe, Very Severe) through word dropping, filler insertion, and paraphasia substitution. Overall, we found, compared to human-elicited transcripts, Mistral 7b Instruct best captures key aspects of linguistic degradation observed in aphasia, showing realistic directional changes in NDW, word count, and word length amongst the synthetic generation methods. Based on the results, future work should plan to create a larger dataset, fine-tune models for better aphasic representation, and have SLPs assess the realism and usefulness of the synthetic transcripts.