相关论文: Pay (Cross) Attention to the Melody: Curriculum Ma…

Code LLMs have emerged as a specialized research field, with remarkable studies dedicated to enhancing model's coding capabilities through fine-tuning on pre-trained models. Previous fine-tuning approaches were typically tailored to…

The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without additional training. In current AV-LLMs, audio and video features are typically…

We present a hybrid neural network and rule-based system that generates pop music. Music produced by pure rule-based systems often sounds mechanical. Music produced by machine learning sounds better, but still lacks hierarchical temporal…

Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue…

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

Lack of standardization and various intrinsic parameters for magnetic resonance (MR) image acquisition results in heterogeneous images across different sites and devices, which adversely affects the generalization of deep neural networks.…

We investigate multi-stage pretraining for prosody modeling in diffusion-based TTS. A speaker-conditioned dual-stream encoder is trained with masked language modeling followed by SigLIP-style cross-modal contrastive learning using…

We propose Serenade, a novel framework for the singing style conversion (SSC) task. Although singer identity conversion has made great strides in the previous years, converting the singing style of a singer has been an unexplored research…

Compositing is one of the most important editing operations for images and videos. The process of improving the realism of composite results is often called harmonization. Previous approaches for harmonization mainly focus on images. In…

Contrastive learning is a powerful way of learning multimodal representations across various domains such as image-caption retrieval and audio-visual representation learning. In this work, we investigate if these findings generalize to the…

Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced…

Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and…

In this work, we investigate the personalization of text-to-music diffusion models in a few-shot setting. Motivated by recent advances in the computer vision domain, we are the first to explore the combination of pre-trained text-to-audio…

Research on style transfer and domain translation has clearly demonstrated the ability of deep learning-based algorithms to manipulate images in terms of artistic style. More recently, several attempts have been made to extend such…

Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech and audio, its…

Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its performance. Metric learning technology is often applied to…

Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previously learned ones. However, existing methods mainly focus…

Public Code Review (PCR) can be implemented through a Software Question Answering (SQA) community, which facilitates high knowledge dissemination. Current methods mainly focus on the reviewer's perspective, including finding a capable…