1

FormerReckoning: Physics Inspired Transformer for Accurate Inertial Navigation
Although modern localization methods have achieved remarkable accuracy with various sensors, there are still some circumstances where …
PDF Cite ACM
FormerReckoning: Physics Inspired Transformer for Accurate Inertial Navigation
Beyond Aggregation: Efficient Federated Model Consolidation with Heterogeneity-Adaptive Weights Diffusion
TBD
Cite
Beyond Aggregation: Efficient Federated Model Consolidation with Heterogeneity-Adaptive Weights Diffusion
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction …
Cite Code arXiv
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Enhancing Emotion Prediction and Recognition in Conversation through Fine-Grained Emotional Cue Analysis and Cross-Modal Fusion
The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual …
Cite arXiv Springer
Enhancing Emotion Prediction and Recognition in Conversation through Fine-Grained Emotional Cue Analysis and Cross-Modal Fusion
RREH: Reconstruction Relations Embedded Hashing for Semi-Paired Cross-Modal Retrieval
Known for efficient computation and easy storage, hashing has been extensively explored in cross-modal retrieval. The majority of …
Cite arXiv Springer
RREH: Reconstruction Relations Embedded Hashing for Semi-Paired Cross-Modal Retrieval
RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis
Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing …
Cite arXiv Springer
RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis
Retrieval-Augmented Audio Deepfake Detection
With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of …
Cite arXiv ACM
Retrieval-Augmented Audio Deepfake Detection
CONTUNER: Singing Voice Beautifying with Pitch and Expressiveness Condition
Singing voice beautifying is a novel task that has application value in people’s daily life, aiming to correct the pitch of the …
Cite arXiv DEMO IEEE
CONTUNER: Singing Voice Beautifying with Pitch and Expressiveness Condition
EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning
Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot …
Cite arXiv DEMO IEEE
EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning
Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning
Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying …
Cite arXiv IEEE
Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning