Home
People
Events
Research
Publications
Contact
News
1
FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer
Federated Learning (FL) has been widely con- cerned for it enables decentralized learning while ensuring data privacy. However, most …
Chenghao Liu
,
Xiaoyang Qu
,
Jianzong Wang
,
Jing Xiao
PDF
Cite
arXiv
IJCAI
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world …
Jinggang Chen
,
Junjie Li
,
Xiaoyang Qu
,
Jianzong Wang
,
Jiguang Wan
,
Jing Xiao
PDF
Cite
Poster
Slides
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains …
Tong Ye
,
Shijing Si
,
Jianzong Wang
,
Ning Cheng
,
Zhitao Li
,
Jing Xiao
PDF
Cite
arXiv
AAAI
PMVC: Data Augmentation-Based Prosody Modeling for Expressive Voice Conversion
Voice conversion as the style transfer task applied to speech, refers to converting one person’s speech into a new speech that …
Yimin Deng
,
Huaizhen Tang
,
Xulong Zhang
,
Jianzong Wang
,
Ning Cheng
,
Jing Xiao
PDF
Cite
arXiv
DEMO
ACM
Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning
This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video …
Liang Wang
,
Kai Lu
,
Nan Zhang
,
Xiaoyang Qu
,
Jianzong Wang
,
Jiguang Wan
,
Guokuan Li
,
Jing Xiao
Cite
arXiv
CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation
Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning …
Yimin Deng
,
Xulong Zhang
,
Jianzong Wang
,
Ning Cheng
,
Jing Xiao
Cite
arXiv
IEEE
CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embedding
This paper proposes a talking face generation method named “CP-EB” that takes an audio signal as input and a person image as reference, …
Jianzong Wang
,
Yimin Deng
,
Ziqi Liang
,
Xulong Zhang
,
Ning Cheng
,
Jing Xiao
Cite
arXiv
IEEE
DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation
Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this …
Jianzong Wang
,
Pengcheng Li
,
Xulong Zhang
,
Ning Cheng
,
Jing Xiao
Cite
arXiv
IEEE
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The …
Haoyan Yang
,
Zhitao Li
,
Yong Zhang
,
Jianzong Wang
,
Ning Cheng
,
Ming Li
,
Jing Xiao
PDF
Cite
arXiv
ACL
VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model
Speaker Verification (SV) performance gets worse as utterances get shorter. To this end, we propose a new architecture called …
Yayun He
,
Zuheng Kang
,
Jianzong Wang
,
Junqing Peng
,
Jing Xiao
Cite
arXiv
IEEE
«
»
Cite
×