# GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation

arXiv: https://arxiv.org/abs/2606.10464 · HTML: https://mlsanity.com/paper/2606.10464/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2026.

## Built on by (most cited first, 2 of 2)

- [Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs](https://mlsanity.com/paper/2609.17981/) (2026)
- [AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models](https://mlsanity.com/paper/2609.23979/) (2026)

## Abstract (arXiv)

Transformer-based Speech Foundation Models excel in most Automatic Speech Recognition tasks but often suffer performance degradation when applied to domains with mismatched acoustic characteristics. While Parameter Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), adjust global attention, they lack the local context modeling crucial for capturing domain-specific variations. We propose GC-LoRA, a novel adapter architecture that injects Conformer-style local convolutional processing into pretrained Transformer encoders. By integrating a lightweight adapter to encoder attention output projections, our method efficiently captures local acoustic dependencies without disrupting pretrained global representations. Experiments across diverse datasets (acoustically-degraded, bandlimited, dialectal, child) demonstrate the efficacy of our approach, achieving Word Error Rate (WER) reductions of up to 10.9% compared to baselines while adding minimal trainable parameters.