PulseAugur
EN
LIVE 18:32:19

Personalized Federated Learning Improves Dysarthric Speech Recognition

By PulseAugur Editorial · [2 sources] ·

Researchers have developed new aggregation strategies for personalized federated learning to improve speech recognition for individuals with dysarthria. The proposed methods, focusing on parameter-based and embedding-based averaging, aim to address heterogeneity issues inherent in federated learning. Experiments on the UASpeech and TORGO datasets demonstrated significant reductions in Word Error Rate (WER) compared to the baseline regularized FedAvg approach. AI

IMPACT Enhances accessibility of speech recognition technology for individuals with speech impairments.

RANK_REASON The cluster contains an academic paper detailing new methods for personalized federated learning.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Personalized Federated Learning Improves Dysarthric Speech Recognition

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Tao Zhong, Mengzhe Geng, Jiajun Deng, Shujie Hu, Xunying Liu ·

    Towards Personalized Federated Learning for Dysarthric Speech Recognition

    arXiv:2606.13253v1 Announce Type: cross Abstract: Speech recognition is challenging for dysarthric speakers. While federated learning (FL)-based ASR can be an effective tool for protecting privacy, it suffers from heterogeneity issues caused by speaker variability. Forcing all sp…

  2. arXiv cs.AI TIER_1 English(EN) · Xunying Liu ·

    Towards Personalized Federated Learning for Dysarthric Speech Recognition

    Speech recognition is challenging for dysarthric speakers. While federated learning (FL)-based ASR can be an effective tool for protecting privacy, it suffers from heterogeneity issues caused by speaker variability. Forcing all speakers to share the same model components can be s…

RELATED ENTITIES

RELATED TOPICS