8 citations · 19 across the 19 of their papers we have counts for
19 papers
ProLombard: Structured Multi-Scale Modeling for Normal-to-Lombard Speech Conversion
Hongyang Chen, Xinmeng Xu, Youqiang Zheng +5
Normal-to-Lombard (N2L) speech conversion aims to improve speech intelligibility in noisy environments by transforming normal speech into Lombard-style speech while preserving ling…
Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning
Xinmeng Xu, Haoran Xie, S. Joe Qin +3
Stage-wise audio-visual encoders propagate fused intermediate states across layers, making the formation of later representations depend on the readiness of earlier fusion states.…
Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model
Jizhen Li, Weiping Tu, Yuhong Yang +3
Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to subs…
SuperCodec: A Neural Speech Codec with Selective Back-Projection Network
Youqiang Zheng, Weiping Tu, Li Xiao +1
Neural speech coding is a rapidly developing topic, where state-of-the-art approaches now exhibit superior compression performance than conventional methods. Despite significant pr…
Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer
Jizhen Li, Xinmeng Xu, Weiping Tu +2
Recent speech enhancement methods based on convolutional neural networks (CNNs) and transformer have been demonstrated to efficaciously capture time-frequency (T-F) information on…
SE Territory: Monaural Speech Enhancement Meets the Fixed Virtual Perceptual Space Mapping
Xinmeng Xu, Yuhong Yang, Weiping Tu
Monaural speech enhancement has achieved remarkable progress recently. However, its performance has been constrained by the limited spatial cues available at a single microphone. T…
PCNN: A Lightweight Parallel Conformer Neural Network for Efficient Monaural Speech Enhancement
Xinmeng Xu, Weiping Tu, Yuhong Yang
Convolutional neural networks (CNN) and Transformer have wildly succeeded in multimedia applications. However, more effort needs to be made to harmonize these two architectures eff…
Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation
Chang Han, Xinmeng Xu, Weiping Tu +2
Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and in…
CQNV: A combination of coarsely quantized bitstream and neural vocoder for low rate speech coding
Youqiang Zheng, Li Xiao, Weiping Tu +2
Recently, speech codecs based on neural networks have proven to perform better than traditional methods. However, redundancy in traditional parameter quantization is visible within…
All Information is Necessary: Integrating Speech Positive and Negative Information by Contrastive Learning for Speech Enhancement
Xinmeng Xu, Weiping Tu, Chang Han +1
Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g.,…
Selector-Enhancer: Learning Dynamic Selection of Local and Non-local Attention Operation for Speech Enhancement
Xinmeng Xu, Weiping Tu, Yuhong Yang
Attention mechanisms, such as local and non-local attention, play a fundamental role in recent deep learning based speech enhancement (SE) systems. However, natural speech contains…
Injecting Spatial Information for Monaural Speech Enhancement via Knowledge Distillation
Xinmeng Xu, Weiping Tu, Yuhong Yang
Monaural speech enhancement (SE) provides a versatile and cost-effective approach to SE tasks by utilizing recordings from a single microphone. However, the monaural SE lags perfor…
Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention
Xinmeng Xu, Yang Wang, Jie Jia +2
Audio-visual speech enhancement system is regarded as one of promising solutions for isolating and enhancing speech of desired speaker. Typical methods focus on predicting clean sp…
GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block
Xinmeng Xu, Yang Wang, Jie Jia +2
For monaural speech enhancement, contextual information is important for accurate speech estimation. However, commonly used convolution neural networks (CNNs) are weak in capturing…
Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention
Xinmeng Xu, Rongzhi Gu, Yuexian Zou
Hand-crafted spatial features, such as inter-channel intensity difference (IID) and inter-channel phase difference (IPD), play a fundamental role in recent deep learning based dual…
U-Former: Improving Monaural Speech Enhancement with Multi-head Self and Cross Attention
Xinmeng Xu, Jianjun Hao
For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing te…
VSEGAN: Visual Speech Enhancement Generative Adversarial Network
Xinmeng Xu, Yang Wang, Dongxiang Xu +4
Speech enhancement is an essential task of improving speech quality in noise scenario. Several state-of-the-art approaches have introduced visual information for speech enhancement…
AMFFCN: Attentional Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement
Xinmeng Xu, Jianjun Hao
Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting…
Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement
Xinmeng Xu, Jianjun Hao
Speech enhancement can potentially benefit from the visual information from the target speaker, such as lip movement and facial expressions, because the visual aspect of speech is…