What type of study is this?

This is a Quantitative Study study.

September 30, 2025Open Access

Exploring Generative Error Correction for Dysarthric Speech Recognition

Key Points

Proposed framework significantly enhances the transcription accuracy of dysarthric speech using generative error correction.
Experiments on the Speech Accessibility Project dataset reveal challenges in single-word recognition, emphasizing the complexity of dysarthric speech transcription.
Our method employs a two-stage approach, combining speech recognition models with LLM-based generative error correction to improve overall performance.
The analysis shows the crucial interplay between acoustic and linguistic modeling in accurately recognizing dysarthric speech.

Abstract

Despite the remarkable progress in end-to-end Automatic Speech Recognition (ASR) engines, accurately transcribing dysarthric speech remains a major challenge. In this work, we proposed a two-stage framework for the Speech Accessibility Project Challenge at INTERSPEECH 2025, which combines cutting-edge speech recognition models with LLM-based generative error correction (GER). We assess different configurations of model scales and training strategies, incorporating specific hypothesis selection to improve transcription accuracy. Experiments on the Speech Accessibility Project dataset demonstrate the strength of our approach on structured and spontaneous speech, while highlighting challenges in single-word recognition. Through comprehensive analysis, we provide insights into the complementary roles of acoustic and linguistic modeling in dysarthric speech recognition

Read Full Paperexternally

Ask AI

Mark Helpful

Bookmark

Relay

View Full Paper