Search Results for author:
Found 42 papers, 26 papers with code
Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective
Current neural networks often employ multi-domain-learning or attribute-injecting mechanisms to incorporate non-independent and identically distributed (non-IID) information for text understanding tasks by capturing individual characteristics and the relationships among samples.
Audio Visual Segmentation Through Text Embeddings
Recent works attempt to overcome the challenge of limited data by leveraging the segmentation foundation model, SAM, prompting it with audio to enhance its ability to segment sounding source objects.
ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
The database contains attacks generated with 32 different algorithms, also crowdsourced, and optimised to varying degrees using new surrogate detection models.
A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging
This study introduces SAMatch, a SAM-guided Match-based framework for semi-supervised medical image segmentation, aimed at improving pseudo label quality in data-scarce scenarios.
Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions
Current emotional text-to-speech (TTS) systems face challenges in mimicking a broad spectrum of human emotions due to the inherent complexity of emotions and limitations in emotional speech datasets and models.
SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge
With the advancements in singing voice generation and the growing presence of AI singers on media platforms, the inaugural Singing Voice Deepfake Detection (SVDD) Challenge aims to advance research in identifying AI-generated singing voices from authentic singers.
A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake Detection
Additionally, to ensure the credibility of detection methods, it is beneficial for the model to interpret which cues from the video indicate it is fake.
CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection
Addressing these gaps, we introduce CtrSVDD, a large-scale, diverse collection of bonafide and deepfake singing vocals.
SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
The rapid advancement of AI-generated singing voices, which now closely mimic natural human singing and align seamlessly with musical scores, has led to heightened concerns for artists and the music industry.
Prior Frequency Guided Diffusion Model for Limited Angle (LA)-CBCT Reconstruction
PFGDM-B, on the other hand, continuously applies the prior CT information condition in every reconstruction step, while with a decaying mechanism, to gradually phase out the reconstruction guidance from the prior CT scans.
Personalized LoRA for Human-Centered Text Understanding
Effectively and efficiently adapting a pre-trained language model (PLM) for human-centered text understanding (HCTU) is challenging since user tokens are million-level in most personalized applications and do not have concrete explicit semantics.
Parameterized Decision-making with Multi-modal Perception for Autonomous Driving
Autonomous driving is an emerging technology that has advanced rapidly over the last decade.
Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech
In this work, we propose to learn the AV representation from categorical emotion labels of speech.
FDDM: Unsupervised Medical Image Translation with a Frequency-Decoupled Diffusion Model
This anatomical information then guides a subsequent diffusion model to generate high-quality CT images.
nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance
To combine the strengths of foundational and domain-specific models, we propose nnSAM, integrating SAM's robust feature extraction with nnUNet's automatic configuration to enhance segmentation accuracy on small datasets.
SingFake: Singing Voice Deepfake Detection
These unique properties make singing voice deepfake detection a relevant but significantly different problem from synthetic speech detection.
Mitigating Cross-Database Differences for Learning Unified HRTF Representation
We further show that these normalized HRTFs can be used to learn a more unified HRTF representation across databases than the prior art.
SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation
Image translation has wide applications, such as style transfer and modality conversion, usually aiming to generate images having both high degrees of realism and faithfulness.
Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models
However, for medical image translation, the existing diffusion models are deficient in accurately retaining structural information since the structure details of source domain images are lost during the forward diffusion process and cannot be fully recovered through learned reverse diffusion, while the integrity of anatomical structures is extremely important in medical images.
ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge
The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a specialized language model with enhanced accuracy in medical advice.
SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing
Our previous research on one-class learning has improved the generalization ability to unseen attacks by compacting the bona fide speech in the embedding space.
HRTF Field: Unifying Measured HRTF Magnitude Representation with Neural Fields
In this work, we propose to use neural fields, a differentiable representation of functions through neural networks, to model HRTFs with arbitrary spatial sampling schemes.
Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers
For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients.
Predicting Global HRTFs From Scanned Head Geometry Using Deep Learning and Compact Representations
For the HRTF data, we use truncated spherical harmonic (SH) coefficients to represent the HRTF magnitudes and onsets.
LViT: Language meets Vision Transformer in Medical Image Segmentation
In our LViT model, medical text annotation is incorporated to compensate for the quality deficiency in image data.
Ranked #3 on
Medical Image Segmentation
on MoNuSeg
Rethinking Audio-visual Synchronization for Active Speaker Detection
This clarification of definition is motivated by our extensive experiments, through which we discover that existing ASD methods fail in modeling the audio-visual synchronization and often classify unsynchronized videos as active speaking.
Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping
For instance, the model trained on a dataset with specific imaging parameters cannot be well applied to other datasets with different imaging parameters.
A Probabilistic Fusion Framework for Spoofing Aware Speaker Verification
We further propose fusion strategies for direct inference and fine-tuning to predict the SASV score based on the framework.
UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021
Different from previous ASVspoof challenges, the LA task this year presents codec and transmission channel variability, while the new task DF presents general audio compression.
Intentional Deep Overfit Learning (IDOL): A Novel Deep Learning Strategy for Adaptive Radiation Therapy
Finally, in the sCT reconstruction task, the MAE is reduced from 68 to 22 HU by utilizing the IDOL framework.
An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems
Spoofing countermeasure (CM) systems are critical in speaker verification; they aim to discern spoofing attacks from bona fide speech trials.
One-class learning towards generalized voice spoofing detection
Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion.
Speech Driven Talking Face Generation from a Single Image and an Emotion Condition
Visual emotion expression plays an important role in audiovisual speech communication.
Visualizing Deep Learning-based Radio Modulation Classifier
Extensive numerical results show both the CNN-based classifier and LSTM-based classifier extract similar radio features relating to modulation reference points.
Data Augmentation for Deep Learning-based Radio Modulation Classification
Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience.
Synthetic Defocus and Look-Ahead Autofocus for Casual Videography
We present a system that synthetically renders refocusable video from a deep DOF video shot with a smartphone, and analyzes future video frames to deliver context-aware autofocus for the current frame.
The normalized Laplacian spectra of subdivision vertex-edge neighbourhood vertex(edge)-corona for graphs
Whereafter, the normalized Laplacian spectra of $G_1^S\bowtie (G_2^V\cup G_3^E)$ and $G_1^S\diamondsuit(G_2^V\cup G_3^E)$ are respectively determined in terms of the corresponding normalized Laplacian spectra of the connected regular graphs $G_{1}$, $G_{2}$ and $G_{3}$, which extend the corresponding results of [A. Das, P. Panigrahi, Linear Multil.
Combinatorics
YNU-HPCC at SemEval-2018 Task 1: BiLSTM with Attention based Sentiment Analysis for Affect in Tweets
The useful BiLSTM (Bidirectional Long-Short Term Memory) model with attention mechanism was mainly applied for our system.
YNU-HPCC at IJCNLP-2017 Task 5: Multi-choice Question Answering in Exams Using an Attention-based LSTM Model
A shared task is a typical question answering task that aims to test how accurately the participants can answer the questions in exams.
Constructing multi-modality and multi-classifier radiomics predictive models through reliable classifier fusion
First, the predictive performance of the model may be reduced when features extracted from an individual imaging modality are blindly combined into a single predictive model.
YNU-HPCC at EmoInt-2017: Using a CNN-LSTM Model for Sentiment Intensity Prediction
In this paper, we present a system that uses a convolutional neural network with long short-term memory (CNN-LSTM) model to complete the task.
