arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.18533eess.AScs.AI
收藏

TS-URGENet:一种三阶段通用、鲁棒且可泛化的语音增强网络

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network

Nanjing University(南京大学);Horizon Robotics

Xiaobin Rong, Dahan Wang, Qinwen Hu, Yushi Wang, Yuxiang Hu, Jing Lu

AI总结:

针对通用语音增强中多种失真和输入格式的挑战,提出三阶段(填充、分离、恢复)TS-URGENet网络,在Interspeech 2025 URGENT挑战赛赛道1中排名第二。

摘要:

通用语音增强旨在处理具有不同失真和输入格式的输入语音。为应对这一挑战,我们提出了TS-URGENet,一种三阶段通用、鲁棒且可泛化的语音增强网络。为处理各种失真,所提出的系统采用了一种新颖的三阶段架构,包括填充阶段、分离阶段和恢复阶段。填充阶段通过在噪声干扰下初步填充丢失区域来减轻丢包影响,确保信号连续性。分离阶段抑制噪声、混响和削波失真,以提高语音清晰度。最后,恢复阶段补偿带宽限制、编解码器伪影和残余丢包失真,细化整体语音质量。我们提出的TS-URGENet在Interspeech 2025 URGENT挑战赛中取得了杰出性能,在赛道1中排名第二。

英文摘要:

Universal speech enhancement aims to handle input speech with different distortions and input formats. To tackle this challenge, we present TS-URGENet, a Three-Stage Universal, Robust, and Generalizable speech Enhancement Network. To address various distortions, the proposed system employs a novel three-stage architecture consisting of a filling stage, a separation stage, and a restoration stage. The filling stage mitigates packet loss by preliminarily filling lost regions under noise interference, ensuring signal continuity. The separation stage suppresses noise, reverberation, and clipping distortion to improve speech clarity. Finally, the restoration stage compensates for bandwidth limitation, codec artifacts, and residual packet loss distortion, refining the overall speech quality. Our proposed TS-URGENet achieved outstanding performance in the Interspeech 2025 URGENT Challenge, ranking 2nd in Track 1.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑