Aphasia is a language disorder that affects the speaking ability of millions of patients. This paper presents a new benchmark for Aphasia speech recognition and detection tasks using state-of-the-art speech recognition techniques with the AphsiaBank dataset. Specifically, we introduce two multi-task learning methods based on the CTC/Attention architecture to perform both tasks simultaneously. Our system achieves state-of-the-art speaker-level detection accuracy (97.3%), and a relative WER reduction of 11% for moderate Aphasia patients. In addition, we demonstrate the generalizability of our approach by applying it to another disordered speech database, the DementiaBank Pitt corpus. We will make our all-in-one recipes and pre-trained model publicly available to facilitate reproducibility. Our standardized data preprocessing pipeline and open-source recipes enable researchers to compare results directly, promoting progress in disordered speech processing.
@article{arxiv.2305.13331,
title = {A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning},
author = {Jiyang Tang and William Chen and Xuankai Chang and Shinji Watanabe and Brian MacWhinney},
journal= {arXiv preprint arXiv:2305.13331},
year = {2023}
}
Comments
Accepted at INTERSPEECH 2023. Code: https://github.com/espnet/espnet