paper-with-me

홈 › Papers

Federated Learning in ASR: Not as Easy as You Think

2021-09-30 · Wentao Yu, Jan Freiwald, Sören Tewes, Fabien Huennemeyer, Dorothea Kolossa

With the growing availability of smart devices and cloud services, personal speech assistance systems are increasingly used on a daily basis. Most devices redirect the voice recordings to a central server, which uses them for upgrading the recognizer model. This leads to major privacy concerns, since private data could be misused by the server or third parties. Federated learning is a decentralized optimization strategy that has been proposed to address such concerns. Utilizing this approach, private data is used for on-device training. Afterwards, updated model parameters are sent to the server to improve the global model, which is redistributed to the clients. In this work, we implement federated learning for speech recognition in a hybrid and an end-to-end model. We discuss the outcomes of these systems, which both show great similarities and only small improvements, pointing to a need for a deeper understanding of federated learning for speech recognition.

📄 PDF Abstract BibTeX arXiv:2109.15108

Code (1)

rub-ksv/federated-learning-asr 공식 구현 pytorch

Tasks

Federated Learningspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

2026-09-17 · Jaejun Shim, HyunJin Kim, Young Jin Kim, JinYeong Bak hf

Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing approaches based on uniform length pena…

FederatedScope: A Flexible Federated Learning Platform for Heterogeneity

2022-04-11 · Yuexiang Xie, Zhen Wang, Dawei Gao, Daoyuan Chen 외

Although remarkable progress has been made by existing federated learning (FL) platforms to provide infrastructures for development, these platforms may not well tackle the challenges brought by various types of heteroge…

Federated LearningHyperparameter Optimization

Learning to Stop Overthinking at Test Time

2025-02-16 · Hieu Tran Bao, Nguyen Cong Dat, Nguyen Duc Anh, Hoang Thanh Tung

Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-…

Visual Reasoning

Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR

2025-11-02 · Abdelaziz Bounhar, Hadi Abdine, Evan Dufraisse, Ahmad Chamma 외 arxiv

Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' probl…

Reinforcement Learning

A Secure Aggregation for Federated Learning on Long-Tailed Data

2023-07-17 · Yanna Jiang, Baihe Ma, Xu Wang, Guangsheng Yu 외

As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-taile…

Federated Learning