arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.16136cs.AIcs.CLcs.LGcs.SDeess.AS
收藏

C3LLM:利用大语言模型进行条件多模态内容生成

C3LLM: Conditional Multimodal Content Generation Using Large Language Models

HKUST(香港科技大学);Dartmouth College(达特茅斯学院)

Zixuan Wang, Qinkai Duan, Yu-Wing Tai, Chi-Keung Tang

AI总结:

C3LLM提出一个统一框架,结合视频转音频、音频转文本和文本转音频任务,利用大语言模型作为跨模态桥梁,采用层次化离散音频生成,实现端到端多模态内容生成,提升语义对齐效果。

摘要:

我们提出了C3LLM(条件于三种模态的大语言模型),一种将视频到音频、音频到文本和文本到音频三项任务结合在一起的创新框架。C3LLM将大语言模型(LLM)结构作为桥梁,用于对齐不同模态、综合给定的条件信息,并以离散方式进行多模态生成。我们的贡献如下。首先,我们针对音频生成任务采用了一种带有预训练音频码本的层次化结构。具体来说,我们训练LLM从给定条件生成音频语义标记,并进一步使用非自回归Transformer分层生成不同级别的声学标记,以更好地增强生成音频的保真度。其次,基于LLM最初设计用于通过下一词预测方法处理离散任务的直觉,我们使用离散表示进行音频生成,并将其语义含义压缩到声学标记中,类似于为LLM添加“声学词汇表”。第三,我们的方法将先前的音频理解、视频到音频生成和文本到音频生成任务整合到一个统一模型中,以端到端的方式提供了更高的通用性。我们的C3LLM通过多种自动化评估指标取得了改进的结果,与先前方法相比提供了更好的语义对齐。

英文摘要:

We introduce C3LLM (Conditioned-on-Three-Modalities Large Language Models), a novel framework combining three tasks of video-to-audio, audio-to-text, and text-to-audio together. C3LLM adapts the Large Language Model (LLM) structure as a bridge for aligning different modalities, synthesizing the given conditional information, and making multimodal generation in a discrete manner. Our contributions are as follows. First, we adapt a hierarchical structure for audio generation tasks with pre-trained audio codebooks. Specifically, we train the LLM to generate audio semantic tokens from the given conditions, and further use a non-autoregressive transformer to generate different levels of acoustic tokens in layers to better enhance the fidelity of the generated audio. Second, based on the intuition that LLMs were originally designed for discrete tasks with the next-word prediction method, we use the discrete representation for audio generation and compress their semantic meanings into acoustic tokens, similar to adding "acoustic vocabulary" to LLM. Third, our method combines the previous tasks of audio understanding, video-to-audio generation, and text-to-audio generation together into one unified model, providing more versatility in an end-to-end fashion. Our C3LLM achieves improved results through various automated evaluation metrics, providing better semantic alignment compared to previous methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑