CLAIDec 19, 2025

Incorporating Error Level Noise Embedding for Improving LLM-Assisted Robustness in Persian Speech Recognition

arXiv:2512.17247v1h-index: 1
Originality Incremental advance
AI Analysis

This work addresses robust ASR for Persian in noisy scenarios, which is an incremental improvement over existing methods.

The study tackled the problem of automatic speech recognition (ASR) performance degradation in noisy environments for Persian, a low-resource language, by proposing a noise-sensitive error correction framework using Error Level Noise (ELN) embeddings. The result was a substantial reduction in Word Error Rate (WER) from 31.10% to 24.84% on a challenging test set.

Automatic Speech Recognition (ASR) systems suffer significant performance degradation in noisy environments, a challenge that is especially severe for low-resource languages such as Persian. Even state-of-the-art models such as Whisper struggle to maintain accuracy under varying signal-to-noise ratios (SNRs). This study presents a robust noise-sensitive ASR error correction framework that combines multiple hypotheses and noise-aware modeling. Using noisy Persian speech, we generate 5-best hypotheses from a modified Whisper-large decoder. Error Level Noise (ELN) is introduced as a representation that captures semantic- and token-level disagreement across hypotheses, quantifying the linguistic distortions caused by noise. ELN thus provides a direct measure of noise-induced uncertainty, enabling the LLM to reason about the reliability of each hypothesis during correction. Three models are evaluated: (1) a base LLaMA-2-7B model without fine-tuning, (2) a fine-tuned variant trained on text-only hypotheses, and (3) a noise-conditioned model integrating ELN embeddings at both sentence and word levels. Experimental results demonstrate that the ELN-conditioned model achieves substantial reductions in Word Error Rate (WER). Specifically, on the challenging Mixed Noise test set, the proposed Fine-tuned + ELN (Ours) model reduces the WER from a baseline of 31.10\% (Raw Whisper) to 24.84\%, significantly surpassing the Fine-tuned (No ELN) text-only baseline of 30.79\%, whereas the original LLaMA-2-7B model increased the WER to 64.58\%, demonstrating that it is unable to correct Persian errors on its own. This confirms the effectiveness of combining multiple hypotheses with noise-aware embeddings for robust Persian ASR in noisy real-world scenarios.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes