相关论文: Diff-Foley: Synchronized Video-to-Audio Synthesis …

Latent Video Diffusion Models (LVDMs) have achieved state-of-the-art generative quality for image and video generation; however, they remain brittle under noisy conditioning, where small perturbations in text or multimodal embeddings can…

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly…

Latent diffusion models have shown promising results in audio generation, making notable advancements over traditional methods. However, their performance, while impressive with short audio clips, faces challenges when extended to longer…

We introduce EzAudio, a text-to-audio (T2A) generation framework designed to produce high-quality, natural-sounding sound effects. Core designs include: (1) We propose EzAudio-DiT, an optimized Diffusion Transformer (DiT) designed for audio…

End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike and high-resolution talking videos. However, direct…

Building artificial intelligence (AI) systems on top of a set of foundation models (FMs) is becoming a new paradigm in AI research. Their representative and generative abilities learnt from vast amounts of data can be easily adapted and…

Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel…

Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown comparable performance by…

We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy…

Foley sound, audio content inserted synchronously with videos, plays a critical role in the user experience of multimedia content. Recently, there has been active research in Foley sound synthesis, leveraging the advancements in deep…

The generation of realistic, context-aware audio is important in real-world applications such as video game development. While existing video-to-audio (V2A) methods mainly focus on Foley sound generation, they struggle to produce…

Multimedia generation approaches occupy a prominent place in artificial intelligence research. Text-to-image models achieved high-quality results over the last few years. However, video synthesis methods recently started to develop. This…

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm,…

We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our…

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper…

Significant advancements have been achieved in the realm of large-scale pre-trained text-to-video Diffusion Models (VDMs). However, previous methods either rely solely on pixel-based VDMs, which come with high computational costs, or on…

The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural…

Although lip-to-speech synthesis (L2S) has achieved significant progress in recent years, current state-of-the-art methods typically rely on intermediate representations such as mel-spectrograms or discrete self-supervised learning (SSL)…

With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to…

Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects synchronized with on-screen actions. Foley requires…