When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems

TL;DR

This study systematically evaluates the impact of speech enhancement on modern medical ASR systems and finds that denoising often degrades recognition performance, challenging conventional assumptions about noise reduction benefits.

Contribution

It provides the first comprehensive analysis showing that traditional speech enhancement can harm modern large-scale ASR models in medical settings.

Findings

Enhanced audio increases semWER in all tested configurations.

Modern ASR models are inherently robust to noise without preprocessing.

Speech enhancement may remove features critical for accurate recognition.

Abstract

Speech enhancement methods are commonly believed to improve the performance of automatic speech recognition (ASR) in noisy environments. However, the effectiveness of these techniques cannot be taken for granted in the case of modern large-scale ASR models trained on diverse, noisy data. We present a systematic evaluation of MetricGAN-plus-voicebank denoising on four state-of-the-art ASR systems: OpenAI Whisper, NVIDIA Parakeet, Google Gemini Flash 2.0, Parrotlet-a using 500 medical speech recordings under nine noise conditions. ASR performance is measured using semantic WER (semWER), a normalized word error rate (WER) metric accounting for domain-specific normalizations. Our results reveal a counterintuitive finding: speech enhancement preprocessing degrades ASR performance across all noise conditions and models. Original noisy audio achieves lower semWER than enhanced audio in all 40 tested configurations (4 models x 10 conditions), with degradations ranging from 1.1% to 46.6% absolute semWER increase. These findings suggest that modern ASR models possess sufficient internal noise robustness and that traditional speech enhancement may remove acoustic features critical for ASR. For practitioners deploying medical scribe systems in noisy clinical environments, our results indicate that preprocessing audio with noise reduction techniques might not just be computationally wasteful but also be potentially harmful to the transcription accuracy.