Search Results for author: Xiulian Peng

Found 15 papers, 3 papers with code

Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition

3 code implementations29 Sep 2023 Xiang Li, Jinglu Wang, Xiaohao Xu, Xiulian Peng, Rita Singh, Yan Lu, Bhiksha Raj

We propose a semantic decomposition method based on product quantization, where the multi-source semantics can be decomposed and represented by several disentangled and noise-suppressed single-source semantics.

Quantization

ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression

no code implementations26 May 2023 Yixin Wan, Yuan Zhou, Xiulian Peng, Kai-Wei Chang, Yan Lu

To begin with, we are among the first to comprehensively investigate mainstream KD techniques on DNS models to resolve the two challenges.

Knowledge Distillation

Real-time speech enhancement with dynamic attention span

no code implementations21 Feb 2023 Chengyu Zheng, Yuan Zhou, Xiulian Peng, Yuan Zhang, Yan Lu

For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge.

Acoustic echo cancellation Speech Enhancement

Disentangled Feature Learning for Real-Time Neural Speech Coding

no code implementations22 Nov 2022 Xue Jiang, Xiulian Peng, Yuan Zhang, Yan Lu

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs.

Disentanglement Voice Conversion

Latent-Domain Predictive Neural Speech Coding

no code implementations18 Jul 2022 Xue Jiang, Xiulian Peng, Huaying Xue, Yuan Zhang, Yan Lu

Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods.

Quantization

Cross-Scale Vector Quantization for Scalable Neural Speech Coding

no code implementations7 Jul 2022 Xue Jiang, Xiulian Peng, Huaying Xue, Yuan Zhang, Yan Lu

In this paper, we introduce a cross-scale scalable vector quantization scheme (CSVQ), in which multi-scale features are encoded progressively with stepwise feature fusion and refinement.

Quantization

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

no code implementations4 Jul 2022 Xiaoyu Wang, Xiangyu Kong, Xiulian Peng, Yan Lu

In this paper we propose a multi-modal multi-correlation learning framework targeting at the task of audio-visual speech separation.

Contrastive Learning Speech Separation

End-to-End Neural Speech Coding for Real-Time Communications

no code implementations24 Jan 2022 Xue Jiang, Xiulian Peng, Chengyu Zheng, Huaying Xue, Yuan Zhang, Yan Lu

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC).

Packet Loss Concealment

Phoneme-based Distribution Regularization for Speech Enhancement

no code implementations8 Apr 2021 Yajing Liu, Xiulian Peng, Zhiwei Xiong, Yan Lu

Specifically, we propose a phoneme-based distribution regularization (PbDr) for speech enhancement, which incorporates frame-wise phoneme information into speech enhancement network in a conditional manner.

Speech Enhancement

Interactive Speech and Noise Modeling for Speech Enhancement

no code implementations17 Dec 2020 Chengyu Zheng, Xiulian Peng, Yuan Zhang, Sriram Srinivasan, Yan Lu

In this paper, we propose a novel idea to model speech and noise simultaneously in a two-branch convolutional neural network, namely SN-Net.

Speaker Separation Speech Enhancement

Frequency-Domain Dynamic Pruning for Convolutional Neural Networks

no code implementations NeurIPS 2018 Zhenhua Liu, Jizheng Xu, Xiulian Peng, Ruiqin Xiong

Deep convolutional neural networks have demonstrated their powerfulness in a variety of applications.

AOD-Net: All-In-One Dehazing Network

1 code implementation ICCV 2017 Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng

This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net).

Image Dehazing object-detection +2

End-to-End United Video Dehazing and Detection

no code implementations12 Sep 2017 Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng

Furthermore, we build an End-to-End United Video Dehazing and Detection Network(EVDD-Net), which concatenates and jointly trains EVD-Net with a video object detection model.

Image Dehazing object-detection +1

An All-in-One Network for Dehazing and Beyond

2 code implementations20 Jul 2017 Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng

This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net).

Image Dehazing object-detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.