English(EN) Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR

模型合并在多领域ASR适应方面展现出潜力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

研究人员探索了模型合并作为一种可扩展的技术，用于在多个领域中适应自动语音识别（ASR）系统。该方法将专门的模型合并成一个更高效的单一模型，避免了重复微调的计算成本。提出了一种新的算法BoostedTSV-M，以提高数值稳定性和缓解秩崩溃，在欧洲葡萄牙语上性能优于传统微调，同时保持了通用性能。 AI

影响模型合并为适应大型ASR模型提供了一种更有效的方式，有望降低计算成本并提高在不同语言领域的性能。

排序理由在arXiv上发表的研究论文，详细介绍了一种新的模型适应技术。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 在arXiv上发表的研究论文，详细介绍了一种新的模型适应技术。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Carlos Carvalho, Francisco Teixeira, Thomas Rolland, Alberto Abad · 2026-11-02 05:00

Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR

arXiv:2603.05354v2 Announce Type: replace Abstract: Model merging is a scalable alternative to multi-task training that combines the capabilities of multiple specialised models into a single model. This is particularly attractive for large speech foundation models, which are typi…