Papers › Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition

Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition

28 Mar 2022arXiv:2203.14838archive 2025-07-28

Yuchen Hu, Nana Hou, Chen Chen, Eng Siong Chng

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e., over-suppression. To alleviate this, we propose a dual-path style learning approach for end-to-end noise-robust speech recognition (DPSL-ASR). Specifically, we first introduce clean speech feature along with the fused feature from IFF-Net as dual-path inputs to recover the suppressed information. Then, we propose style learning to map the fused feature close to clean feature, in order to learn latent speech information from the latter, i.e., clean "speech style". Furthermore, we also minimize the distance of final ASR outputs in two paths to improve noise-robustness. Experiments show that the proposed approach achieves relative word error rate (WER) reductions of 10.6% and 8.6% over the best IFF-Net baseline, on RATS and CHiME-4 datasets respectively.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yuchen005/dpsl-asr officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Robust Speech RecognitionSpeech EnhancementSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Rats

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections