Making Machines Sound Sarcastic: LLM-Enhanced and Retrieval-Guided Sarcastic Speech Synthesis
arxiv.org·4h
A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data
arxiv.org·1d
MSF-SER: Enriching Acoustic Modeling with Multi-Granularity Semantics for Speech Emotion Recognition
arxiv.org·1d
The Feature Understandability Scale for Human-Centred Explainable AI: Assessing Tabular Feature Importance
arxiv.org·4h
Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
arxiv.org·4h
Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation
arxiv.org·3d
RVFL-X: A Novel Randomized Network Based on Complex Transformed Real-Valued Tabular Datasets
arxiv.org·4h
SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling
arxiv.org·2d
Loading...Loading more...