paper-with-me

Papers

MoDiCoL: A Modular Diagnostic Continual Learning Dataset for Robust Speech Recognition

2026-06-12 · Theresa Pekarek Rosin, Matthias Kerzel, Stefan Wermter arxiv

Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caused by recording conditions, accents, speech impairments, and noise. Existing datasets and benchmarks typically isolate these factors, which overlooks their co-occurrence in real-world applications. In this paper, we argue that model robustness can be treated as a dynamic capability that continually develops, and we introduce MoDiCoL, a Modular Diagnostic Continual Learning dataset designed for controlled analysis of linguistic content, speaker characteristics, and acoustic environments. Furthermore, we propose a real-world-inspired continual learning curriculum to simulate incremental updates and study how robustness is acquired, transferred, and forgotten. We evaluate three continual learning strategies and provide detailed insights into robustness under evolving conditions.

📄 PDF Abstract BibTeX arXiv:2606.14459

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningSpeech Recognition

Similar Papers 제목 키워드 기반

SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing

2026-01-14 · Ziyang Ma, Guanrou Yang, Wenxi Chen, Zhifu Gao 외 arxiv

The recent surge in open-source Multimodal Large Language Models (MLLM) frameworks, such as LLaVA, provides a convenient kickoff for artificial intelligence developers and researchers. However, most of the MLLM framework…

parameter-efficient fine-tuningSpeech RecognitionAudio captioning

Continual Learning in Machine Speech Chain Using Gradient Episodic Memory

2024-11-27 · Geoffrey Tyndall, Kurniawati Azizah, Dipta Tanaya, Ayu Purwarianti 외

Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introdu…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Continual Learningspeech-recognition+3

A Probabilistic Framework for Modular Continual Learning

2023-06-11 · Lazar Valkov, Akash Srivastava, Swarat Chaudhuri, Charles Sutton

Modular approaches that use a different composition of modules for each problem are a promising direction in continual learning (CL). However, searching through the large, discrete space of module compositions is challen…

Continual Learning

Distributed Continual Learning

2024-05-23 · Long Le, Marcel Hussing, Eric Eaton

This work studies the intersection of continual and federated learning, in which independent agents face unique tasks in their environments and incrementally develop and share knowledge. We introduce a mathematical frame…

Continual LearningFederated Learning

Dynamically Modular and Sparse General Continual Learning

2023-01-02 · Arnav Varma, Elahe Arani, Bahram Zonooz

Real-world applications often require learning continuously from a stream of data under ever-changing conditions. When trying to learn from such non-stationary data, deep neural networks (DNNs) undergo catastrophic forge…

Continual Learning