Search Results for author:
Found 36 papers, 10 papers with code
Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks
To obtain sufficient knowledge for crafting adversarial examples, previous methods query the target model with inputs that are perturbed with different searching directions.
Cross Attention Augmented Transducer Networks for Simultaneous Translation
This paper proposes a novel architecture, Cross Attention Augmented Transducer (CAAT), for simultaneous translation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Psy-Insight: Explainable Multi-turn Bilingual Dataset for Mental Health Counseling
Psy-Insight is not only suitable for tasks such as label recognition but also meets the need for training LLMs to act as empathetic counselors through logical reasoning.
Psy-Copilot: Visual Chain of Thought for Counseling
Moreover, we have developed Psy-Copilot, which is a conversational AI assistant designed to assist human psychological therapists in their consultations.
Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition
To address the limitation in multimodal emotion recognition (MER) performance arising from inter-modal information fusion, we propose a novel MER framework based on multitask learning where fusion occurs after alignment, called Foal-Net.
SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion
Diffusion-based singing voice conversion (SVC) models have shown better synthesis quality compared to traditional methods.
Near-Field Channel Estimation for Extremely Large-Scale Terahertz Communications
Building on this, we propose four estimation frameworks using the sparse recovery theory: polar-domain estimation (PD-E), multi-angular-domain estimation (MAD-E), two-stage polar-angular-domain estimation (TS-PAD-E), and two-dimensional polar-angular-domain estimation (2D-PAD-E).
Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model
Recent advances in large language models (LLMs) and development of audio codecs greatly propel the zero-shot TTS.
Perceptual learning in contour detection transfer across changes in contour path and orientation
The integration of local elements into shape contours is critical for target detection and identification in cluttered scenes.
Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation
Drawing inspiration from state-of-the-art Text-to-Image (T2I) diffusion models, we introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent generative strengths and precise cross-modal alignment.
Ranked #6 on
Audio Generation
on AudioCaps
(FAD metric)
CRB Minimization for RIS-aided mmWave Integrated Sensing and Communications
In this paper, reconfigurable intelligent surface (RIS) is employed in a millimeter wave (mmWave) integrated sensing and communications (ISAC) system.
Frame-level emotional state alignment method for speech emotion recognition
To address this problem, we propose a frame-level emotional state alignment method for SER.
Hypergraph Enhanced Knowledge Tree Prompt Learning for Next-Basket Recommendation
To settle the above challenges, we propose a novel method HEKP4NBR, which transforms the knowledge graph (KG) into prompts, namely Knowledge Tree Prompt (KTP), to help PLM encode the OOV item IDs in the user's basket sequence.
CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis
In this paper, we introduce a contrastive learning-based CSS framework, CONCSS.
Mutual Information-Based Integrated Sensing and Communications: A WMMSE Framework
In this letter, a weighted minimum mean square error (WMMSE) empowered integrated sensing and communication (ISAC) system is investigated.
M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis
However, it is still a challenge to comprehensively model the conversation, and a majority of conversational TTS systems only focus on extracting global information and omit local prosody features, which contain important fine-grained information like keywords and emphasis.
Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels.
DKT-STDRL: Spatial and Temporal Representation Learning Enhanced Deep Knowledge Tracing for Learning Performance Prediction
Then, the spatial features are connected with the original students' exercise features as joint learning features.
A Keypoint Based Enhancement Method for Audio Driven Free View Talking Head Synthesis
Then we used keypoint decomposition to extract video synthesis controlling parameters from the backend output and the source image.
Towards Lightweight Black-Box Attacks against Deep Neural Networks
As it is hard to mitigate the approximation error with few available samples, we propose Error TransFormer (ETF) for lightweight attacks.
ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress.
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.
Speech Emotion Recognition via Contrastive Loss under Siamese Networks
It outperforms the baseline system that is optimized without the contrastive loss function with 1. 14% and 2. 55% in the weighted accuracy and the unweighted accuracy, respectively.
Expression Analysis Based on Face Regions in Read-world Conditions
To sum up, the contributions of this paper lie in two areas: 1) We visualize concerned areas of human faces in emotion recognition; 2) We analyze the contribution of different face areas to different emotions in real-world conditions through experimental analysis.
On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning
The objective of our proposed method is to transform the features from different tasks into a common feature space in which the tasks are closely related and the shared parameters can be better optimized.
Learning Efficient Lexically-Constrained Neural Machine Translation with External Memory
Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored.
Improving speech emotion recognition via Transformer-based Predictive Coding through transfer learning
I have submitted a new version to arXiv:1910. 13806.
Investigation of Multimodal Features, Classifiers and Fusion Methods for Emotion Recognition
We test our method in the EmotiW 2018 challenge and we gain promising results.
Deep Domain Generalization via Conditional Invariant Adversarial Networks
Under the assumption that the conditional distribution $P(Y|X)$ remains unchanged across domains, earlier approaches to domain generalization learned the invariant representation $T(X)$ by minimizing the discrepancy of the marginal distribution $P(T(X))$.
Ranked #76 on
Domain Generalization
on PACS
Domain Generalization via Conditional Invariant Representation
With the conditional invariant representation, the invariance of the joint distribution $\mathbb{P}(h(X), Y)$ can be guaranteed if the class prior $\mathbb{P}(Y)$ does not change across training and test domains.
Cost-Effective Active Learning for Deep Image Classification
In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner.
DARI: Distance metric And Representation Integration for Person Verification
The past decade has witnessed the rapid development of feature representation learning and distance metric learning, whereas the two steps are often discussed separately.
Ranked #7 on
Person Re-Identification
on SYSU-30k
(using extra training data)
Audio Visual Emotion Recognition with Temporal Alignment and Perception Attention
The other one is locating and re-weighting the perception attentions in the whole audio-visual stream for better recognition.
Deep Boosting: Joint Feature Selection and Analysis Dictionary Learning in Hierarchy
In each layer, we construct a dictionary of filters by combining the filters from the lower layer, and iteratively optimize the image representation with a joint discriminative-generative formulation, i. e. minimization of empirical classification error plus regularization of analysis image generation over training images.
Defuzzify firstly or finally: Dose it matter in fuzzy DEMATEL under uncertain environment?
The results of defuzzification at the first step are not coincide with the results of defuzzification at the final step. It seems that the alternative is to defuzzification in the final step in fuzzy DEMATEL.
