Guardado en:
Detalles Bibliográficos
Autores principales: Chondhekar, Sujal, Murukuri, Vasanth, Vasani, Rushabh, Goyal, Sanika, Badami, Rajshree, Rana, Anushree, SN, Sanjana, Pandia, Karthik, Katiyar, Sulabh, Jagadeesh, Neha, Gulati, Sankalp
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.17562
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912776832679936
author Chondhekar, Sujal
Murukuri, Vasanth
Vasani, Rushabh
Goyal, Sanika
Badami, Rajshree
Rana, Anushree
SN, Sanjana
Pandia, Karthik
Katiyar, Sulabh
Jagadeesh, Neha
Gulati, Sankalp
author_facet Chondhekar, Sujal
Murukuri, Vasanth
Vasani, Rushabh
Goyal, Sanika
Badami, Rajshree
Rana, Anushree
SN, Sanjana
Pandia, Karthik
Katiyar, Sulabh
Jagadeesh, Neha
Gulati, Sankalp
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17562
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems
Chondhekar, Sujal
Murukuri, Vasanth
Vasani, Rushabh
Goyal, Sanika
Badami, Rajshree
Rana, Anushree
SN, Sanjana
Pandia, Karthik
Katiyar, Sulabh
Jagadeesh, Neha
Gulati, Sankalp
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
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.
title When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2512.17562