相关论文: EzAudio: Enhancing Text-to-Audio Generation with E…

Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely,…

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in…

While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods…

Diffusion Transformer (DiT) has demonstrated remarkable performance in text-to-image generation; however, its large parameter size results in substantial inference overhead. Existing parameter compression methods primarily focus on pruning,…

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

Current dialogue generation approaches typically require the complete dialogue text before synthesis and produce a single, inseparable speech containing all voices, making them unsuitable for interactive chat; moreover, they suffer from…

This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text conditions, meanwhile ensuring both modalities are aligned with text. Despite…

Dance-to-music (D2M) generation aims to automatically compose music that is rhythmically and temporally aligned with dance movements. Existing methods typically rely on coarse rhythm embeddings, such as global motion features or binarized…

Recent advances in diffusion-based generative models have enabled high-quality text-to-audio synthesis, but fine-grained acoustic control remains a significant challenge in open-source research. We present Audio Palette, a diffusion…

Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistants. However, most existing approaches are limited to offline processing of complete audio…

The diffusion model has been proven a powerful generative model in recent years, yet remains a challenge in generating visual text. Several methods alleviated this issue by incorporating explicit text position and content as guidance on…

In e-commerce and digital marketing, generating high-fidelity human-product demonstration videos is important for effective product presentation. However, most existing frameworks either fail to preserve the identities of both humans and…

Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow…

Personalized diffusion models have shown remarkable success in Text-to-Image (T2I) generation by enabling the injection of user-defined concepts into diverse contexts. However, balancing concept fidelity with contextual alignment remains a…

Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability…

Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech…

Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data…

Diffusion distillation has dramatically accelerated class-conditional image synthesis, but its applicability to open-ended text-to-image (T2I) generation is still unclear. We present the first systematic study that adapts and compares…

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

Speech tokenizers serve as foundational components for speech language models, yet current designs exhibit several limitations, including: 1) dependence on multi-layer residual vector quantization structures or high frame rates, 2) reliance…