NAaLOSS: Rethinking the Objective of Speech Enhancement

Kuan Hsun Ho*, En Lun Yu, Jeih Weih Hung, Berlin Chen

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

Reducing noise interference is crucial for automatic speech recognition (ASR) in a real-world scenario. However, most single-channel speech enhancement (SE) generates 'processing artifacts' that negatively affect ASR performance. Hence, in this study, we suggest a Noise- and Artifacts-aware loss function, NAaLoss, to ameliorate the influence of artifacts from a novel perspective. NAaLoss considers the loss of estimation, de-artifact, and noise ignorance, enabling the learned SE to individually model speech, artifacts, and noise. We examine two SE models (simple/advanced) learned with NAaLoss under various input scenarios (clean/noisy) using two configurations of the ASR system (with/without noise robustness). Experiments reveal that NAaLoss significantly improves the ASR performance of most setups while preserving the quality of SE toward perception and intelligibility. Furthermore, we visualize artifacts through waveforms and spectrograms, and explain their impact on ASR.

原文英語
主出版物標題Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023
編輯Danilo Comminiello, Michele Scarpiniti
發行者IEEE Computer Society
ISBN(電子)9798350324112
DOIs
出版狀態已發佈 - 2023
事件33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023 - Rome, 意大利
持續時間: 2023 9月 172023 9月 20

出版系列

名字IEEE International Workshop on Machine Learning for Signal Processing, MLSP
2023-September
ISSN(列印)2161-0363
ISSN(電子)2161-0371

會議

會議33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023
國家/地區意大利
城市Rome
期間2023/09/172023/09/20

ASJC Scopus subject areas

  • 人機介面
  • 訊號處理

指紋

深入研究「NAaLOSS: Rethinking the Objective of Speech Enhancement」主題。共同形成了獨特的指紋。

引用此