Entity · paper

SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies

paperactiveprovisionalspeechllm-meets-federated-learning-for-end-to-end-asr-english-and-italian-case-studies-5c48d035·1 events·first seen 45h ago

Aliases: SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies

More like this (12)

Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data SpeechLLM Interleaved Speech Language Models Latently Work In Text Linguistic Monoculture in LLM-Assisted Language Use LLM-augmented clinical NLP pipeline Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR Reinforcement Learning for Language Models Association for Computational Linguistics How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation human-LLM collaborative annotation Audio-LLM StreamingLLM

Recent events (1)

4arXiv · cs.CL·45h ago·source ↗

First systematic study of federated learning for SpeechLLM-based end-to-end ASR

A new arXiv preprint presents the first systematic study of federated training applied to speech language model (SpeechLLM) architectures for end-to-end automatic speech recognition. The authors design a communication-efficient federated optimization strategy addressing gradient overhead and distributed computational constraints, evaluated on English and Italian monolingual ASR tasks. Results show competitive word error rates with reduced communication costs compared to centralized baselines, with ablation studies covering speech encoder architecture choices.

AI Safety Research Enterprise Deployment Patterns SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies