Towards Decoupling Frontend Enhancement And Backend Recognition In Monaural Robust ASR

Abstract

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy conditions compared to an ASR model trained on noisy speech directly. The divide between SE and ASR impedes the progress of robust ASR systems, especially as SE has made major advances in recent years. This paper focuses on eliminating this divide with an ARN (attentive recurrent network) time-domain and a CrossNet time-frequency domain enhancement models. The proposed systems fully decouple frontend enhancement and backend ASR trained only on clean speech. Results on the WSJ, CHiME-2, LibriSpeech, and CHiME-4 corpora demonstrate that ARN and CrossNet enhanced speech both translate to improved ASR results in noisy and reverberant environments, and generalize well to real acoustic scenarios. The proposed system outperforms the baselines trained on corrupted

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyyang2024towards

Related papers

• Time-domain Speech Enhancement For Robust Automatic Speech Recognition (2022)7.16
• Investigation Of Monaural Front-end Processing For Robust ASR Without Retraining Or Joint-training (2018)0.00
• Elevating Robust Multi-talker ASR By Decoupling Speaker Separation And Speech Recognition (2025)0.00
• Improving Noise Robust Automatic Speech Recognition With Single-channel Time-domain Enhancement Network (2020)13.88
• Bridging The Gap: Integrating Pre-trained Speech Enhancement And Recognition Models For Robust Speech Recognition (2024)7.50
• A Conformer-based ASR Frontend For Joint Acoustic Echo Cancellation, Speech Enhancement And Speech Separation (2021)9.23
• End-to-end Dereverberation, Beamforming, And Speech Recognition With Improved Numerical Stability And Advanced Frontend (2021)10.97
• A Universally-deployable ASR Frontend For Joint Acoustic Echo Cancellation, Speech Enhancement, And Voice Separation (2022)5.84