Advancing Dysarthric Speech-to-Text Recognition with LATTE: A Low-Latency Acoustic Modeling Approach for Real-Time Communication.

Dysarthria, a motor speech disorder characterized by slurred and often unintelligible speech, presents substantial challenges for effective communication. Conventional automatic speech recognition systems frequently underperform on dysarthric speech, particularly in severe cases. To address this gap, we introduce low-latency acoustic transcription and textual encoding (LATTE), an advanced framework designed for real-time dysarthric speech recognition. LATTE integrates preprocessing, acoustic processing, and transcription mapping into a unified pipeline, with its core powered by a hybrid architecture that combines convolutional layers for acoustic feature extraction with bidirectional temporal layers for modeling temporal dependencies. Evaluated on the UA-Speech dataset, LATTE achieves a word error rate of 12.5%, phoneme error rate of 8.3%, and a character error rate of 1%. By enabling accurate, low-latency transcription of impaired speech, LATTE provides a robust foundation for enhancing communication and accessibility in both digital applications and real-time interactive environments.

• Publication year

  2026

• Venue

  Big Data

• Publication date

  2026-02-09

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1177/2167647X251411174PMID 41657331
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A novel Swin transformer based framework for speech recognition for dysarthria

  2025cited by this paper
• Dysarthric speech recognition: an investigation on using depthwise separable convolutions and residual connections

  2024cited by this paper
• Robust language independent voice data driven Parkinson's disease detection

  2024cited by this paper
• A Comprehensive Survey on the Data-Driven Approaches used for Tackling the COVID-19 Pandemic

  2024cited by this paper
• Improving cross-lingual low-resource speech recognition by Task-based Meta PolyLoss

  2024cited by this paper
• Data-driven approaches to bridging the gap in health communication disparities: A systematic review

  2024cited by this paper
• Exploration of Whisper fine-tuning strategies for low-resource ASR

  2024cited by this paper
• Intelligent speech technologies for transcription, disease diagnosis, and medical equipment interactive control in smart hospitals: A review

  2023cited by this paper
• A Survey of Automatic Speech Recognition for Dysarthric Speech

  2023cited by this paper
• Deep learning-based speech analysis for Alzheimer’s disease detection: a literature review

  2022cited by this paper
• Biosignal Sensors and Deep Learning-Based Speech Recognition: A Review

  2021cited by this paper
• Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network

  2020cited by this paper
• Dysarthric Speech Recognition using Convolutional Recurrent Neural Networks

  2020cited by this paper
• Investigation of Data Augmentation Techniques for Disordered Speech Recognition

  2020cited by this paper
• An attention Long Short-Term Memory based system for automatic classification of speech intelligibility

  2020cited by this paper
• A Review on Different Approaches for Speech Recognition System

  2015cited by this paper
• The TORGO database of acoustic and articulatory speech from speakers with dysarthria

  2011cited by this paper

• No citing papers are available for this paper.