activity
20192023
most citedSpEx: Multi-Scale Time Domain Speaker Extraction Network

158 citations · 238 across the 20 of their papers we have counts for

collaborators
Showing 2023 · cs.SDShow all

5 papers · 2 filters

cs.SD2023★ 1 cited

The FlySpeech Audio-Visual Speaker Diarization System for MISP Challenge 2022

Li Zhang, Huan Zhao, Yue Li +6

This paper describes the FlySpeech speaker diarization system submitted to the second \textbf{M}ultimodal \textbf{I}nformation Based \textbf{S}peech \textbf{P}rocessing~(\textbf{MI…

cs.SD2023★ 1 cited

MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation

Jun Chen, Wei Rao, Zilin Wang +5

The previous SpEx+ has yielded outstanding performance in speaker extraction and attracted much attention. However, it still encounters inadequate utilization of multi-scale inform…

cs.SD2023

Gesper: A Restoration-Enhancement Framework for General Speech Reconstruction

Wenzhe Liu, Yupeng Shi, Jun Chen +5

This paper describes a real-time General Speech Reconstruction (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This novel proposed system is…

cs.SD2023

Inter-SubNet: Speech Enhancement with Subband Interaction

Jun Chen, Wei Rao, Zilin Wang +5

Subband-based approaches process subbands in parallel through the model with shared parameters to learn the commonality of local spectrums for noise reduction. In this way, they ha…

cs.SD2023

Distance-based Weight Transfer from Near-field to Far-field Speaker Verification

Li Zhang, Qing Wang, Hongji Wang +4

The scarcity of labeled far-field speech is a constraint for training superior far-field speaker verification systems. Fine-tuning the model pre-trained on large-scale near-field s…