DQLoRA: A Lightweight Domain-Aware Denoising ASR via Adapter-guided Distillation

Abstract

We present a demo of DQLoRA, an Adapter-Guided Distillation framework for robust speech recognition under low-resource and noisy conditions. Our method employs a frozen Whisper model as the teacher to provide semantic supervision, and a lightweight Wav2Vec2 student equipped with QLoRA-based Adapters. Training is conducted on the FLEURS dataset augmented with DNS-style noise. The student is optimized by jointly minimizing CTC loss and KL-based distillation loss, enabling efficient adaptation while preserving recognition accuracy.