22 accepted papers
Toxic speech detection has become a crucial challenge in maintaining safe online communication environments. However, existing approaches to toxic speech detection often neglect the contribution of paralinguistic cues, such as emotion, intonation, and speech rate, which are key to detecting speech t
Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking …
Test-Time Adaptation (TTA) enhances model robustness to out-of-distribution (OOD) data by updating the model online during inference, yet existing methods lack theoretical insights into the fundamental causes of performance degradation under domain shifts. Recently, Neural Collapse (NC) has been pro
Large Language Models (LLMs) and causal learning each hold strong potential for clinical decision making (CDM). However, their synergy remains poorly understood, largely due to the lack of systematic benchmarks evaluating their integration in clinical risk prediction. In real-world healthcare, ident
Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present **Instant4D**, a monocular reconstruction system that leverages native 4D representa…
Location-Based Social Networks (LBSNs) offer a rich dataset of user activity at Points-of-Interest (POIs), making next POI recommendation a key task. Traditional algorithms face challenges due to broad searching scopes, affecting recommendation accuracy. Users tend to visit nearby POIs and show temp…
Point cloud completion aims to recover a complete point shape from a partial point cloud. Although existing methods can form satisfactory point clouds in global completeness, they often lose the original geometry details and face the problem of geometric inconsistency between existing point clouds a…
Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is t…
Facial Attribute Manipulation (FAM) through GAN-based methods has been an active topic in computer graphics. Existing works show high editing fidelity on randomly generated faces but suffer from distortion on embedded real faces. We alleviate this issue by dividing it into two sub-problems. First, w…
This paper proposes a novel Deconvolution-enhanced data Augmentation method, DeAug, for ultrasonic-based speaker verification anti-spoofing systems to detect the liveness of voice sources in physical access, which aims to improve the performance of liveness detection on unseen devices where no data…
This paper aims to introduce a robust singing voice synthesis (SVS) system to produce very natural and realistic singing voices efficiently by leveraging the adversarial training strategy. On one hand, we designed simple but generic random area conditional discriminators to help supervise the acoust…
"The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedforward, and high-level information is rarely reused to improve low-level feature learning. To this end, we propose a nov…
Electrocardiogram (ECG) signal based cross-subject emotion recognition methods reduce the influence of individual differences using domain adaptation (DA) techniques. These methods generally assume that the entire unlabeled data of unknown target subjects are available in training phase. However, t…
We propose a novel method for zero-shot cross-lingual TTS task by using multi-stream text encoder and efficient speaker representation. Specifically, a unified multi-stream text encoder that takes both advantages of Transformer and CBHG is proposed to retain multiple hypotheses about input represent…
A trajectory tiling based, hybrid TTS is revisited in this study for improving its synthesis performance. A combination of Transformer encoder and RNN based decoder architecture where two-level, at both word and Chinese phonetic alphabet letter levels, linguistic representation is exploited to gener…
In this paper, we propose a novel method for fast and efficient few-shot TTS task, which is able to disentangle linguistic and speaker representations. Specifically, an adversarial training strategy is firstly employed to wipe out speaker information from the linguistic representations. Then the spe…
The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The mo…
A frame-unit-selection based voice conversion system proposed earlier by us is revisited here to enhance its performance in both speech naturalness and speaker similarity. Speaker independent, bilingual (Mandarin Chinese and American English) deep neural net (DNN) acoustic model’s output, frame-leve…
Although Transformer based neural end-to-end TTS model has demonstrated extreme effectiveness in capturing long-term dependencies and achieved state-of-the-art performance, it still suffers from two problems. 1) limited ability to model sequential and local structures in sequences; 2) heavily rely o…
With the development of globalization, automatic emotion recognition has faced a new challenge in the multi-culture scenario - to generalize across different cultures. Previous works mainly rely on multi-cultural datasets to address the cross-culture discrepancy, which are expensive to collect. In t…
In this paper, we propose a cross-lingual deep neural network (DNN) based submodular unbiased data selection approach for low-resource keyword search (KWS). A small amount (e.g. one hour) of transcribed data is used to conduct cross-lingual transfer. The frame-level senone sequence activated by the…
In this paper, we propose to use acoustic feature based submodular function optimization to select a subset of untranscribed data for manual transcription, and retrain the initial acoustic model with the additional transcribed data. The acoustic features are obtained from an unsupervised Gaussian mi…