Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Xiulian Peng

Xiulian Peng

DasFormer: Deep Alternating Spectrogram Transformer for Multi/Single-Channel Speech Separation

Mar 14, 2023
Shuo Wang, Xiangyu Kong, Xiulian Peng, Mahmood Movassagh, Vinod Prakash, Yan Lu

Figure 1 for DasFormer: Deep Alternating Spectrogram Transformer for Multi/Single-Channel Speech Separation

Figure 2 for DasFormer: Deep Alternating Spectrogram Transformer for Multi/Single-Channel Speech Separation

Figure 3 for DasFormer: Deep Alternating Spectrogram Transformer for Multi/Single-Channel Speech Separation

Figure 4 for DasFormer: Deep Alternating Spectrogram Transformer for Multi/Single-Channel Speech Separation

* 5 pages, accepted by ICASSP2023

Access Paper or Ask Questions

Contrast-PLC: Contrastive Learning for Packet Loss Concealment

Feb 26, 2023
Huaying Xue, Xiulian Peng, Yan Lu

Figure 1 for Contrast-PLC: Contrastive Learning for Packet Loss Concealment

Figure 2 for Contrast-PLC: Contrastive Learning for Packet Loss Concealment

Figure 3 for Contrast-PLC: Contrastive Learning for Packet Loss Concealment

Figure 4 for Contrast-PLC: Contrastive Learning for Packet Loss Concealment

* 5 pages, ICASSP 2023(Accepted)

Access Paper or Ask Questions

Improving Speech Enhancement via Event-based Query

Feb 24, 2023
Yifei Xin, Xiulian Peng, Yan Lu

Figure 1 for Improving Speech Enhancement via Event-based Query

Figure 2 for Improving Speech Enhancement via Event-based Query

Figure 3 for Improving Speech Enhancement via Event-based Query

Figure 4 for Improving Speech Enhancement via Event-based Query

* Accepted by ICASSP2023

Access Paper or Ask Questions

Real-time speech enhancement with dynamic attention span

Feb 21, 2023
Chengyu Zheng, Yuan Zhou, Xiulian Peng, Yuan Zhang, Yan Lu

Figure 1 for Real-time speech enhancement with dynamic attention span

Figure 2 for Real-time speech enhancement with dynamic attention span

Figure 3 for Real-time speech enhancement with dynamic attention span

Figure 4 for Real-time speech enhancement with dynamic attention span

* ICASSP 2023 (Accepted)

Access Paper or Ask Questions

Disentangled Feature Learning for Real-Time Neural Speech Coding

Nov 22, 2022
Xue Jiang, Xiulian Peng, Yuan Zhang, Yan Lu

Figure 1 for Disentangled Feature Learning for Real-Time Neural Speech Coding

Figure 2 for Disentangled Feature Learning for Real-Time Neural Speech Coding

Figure 3 for Disentangled Feature Learning for Real-Time Neural Speech Coding

Figure 4 for Disentangled Feature Learning for Real-Time Neural Speech Coding

* Submitted to ICASSP2023

Access Paper or Ask Questions

Predictive Neural Speech Coding

Jul 18, 2022
Xue Jiang, Xiulian Peng, Huaying Xue, Yuan Zhang, Yan Lu

Figure 1 for Predictive Neural Speech Coding

Figure 2 for Predictive Neural Speech Coding

Figure 3 for Predictive Neural Speech Coding

Figure 4 for Predictive Neural Speech Coding

* Submitted to IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING (TASLP)

Access Paper or Ask Questions

Cross-Scale Vector Quantization for Scalable Neural Speech Coding

Jul 07, 2022
Xue Jiang, Xiulian Peng, Huaying Xue, Yuan Zhang, Yan Lu

Figure 1 for Cross-Scale Vector Quantization for Scalable Neural Speech Coding

Figure 2 for Cross-Scale Vector Quantization for Scalable Neural Speech Coding

Figure 3 for Cross-Scale Vector Quantization for Scalable Neural Speech Coding

Figure 4 for Cross-Scale Vector Quantization for Scalable Neural Speech Coding

* INTERSPEECH 2022(Accepted)

Access Paper or Ask Questions

Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

Jul 04, 2022
Xiaoyu Wang, Xiangyu Kong, Xiulian Peng, Yan Lu

Figure 1 for Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

Figure 2 for Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

Figure 3 for Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

Figure 4 for Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

* 5 pages, accepted by interspeech2022

Access Paper or Ask Questions