A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning

Jiyang Tang, William Chen, Xuankai Chang, Shinji Watanabe, Brian MacWhinney
5/19/2023
eess.AScs.CL

No official code found. Best implementation: espnet/espnet (9,991 stars, Apache-2.0, PyTorch, last commit 2026-04-27).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

espnet/espnetCommunity100%
PyTorchApache-2.0

End-to-End Speech Processing Toolkit

9,9912,444C++, CudaDec 13, 20175 months agoApache-2.0
chainerdeep-learningend-to-endkaldimachine-translation+11 more

Similar Papers

Detecting Speech Abnormalities with a Perceiver-based Sequence Classifier that Leverages a Universal Speech Model

85% match2023

Deploying UDM Series in Real-Life Stuttered Speech Applications: A Clinical Evaluation Framework

83% match2025

Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models

83% match2026

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark

83% match2 repos3112023

Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention

82% match2026

SpeechDx: A Multi-Task Benchmark for Clinical Speech AI

82% match2026

Cite this paper

@article{tang2023benchmark,
  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},
  year   = {2023},
  eprint = {2305.13331},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.13331v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.13331.svg)](https://codeofpaper.com/paper/2305.13331)

Discussion