Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liang, Jinhua, Zhang, Huan, Liu, Haohe, Cao, Yin, Kong, Qiuqiang, Liu, Xubo, Wang, Wenwu, Plumbley, Mark D., Phan, Huy, Benetos, Emmanouil
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.09527
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909197298302976
author Liang, Jinhua
Zhang, Huan
Liu, Haohe
Cao, Yin
Kong, Qiuqiang
Liu, Xubo
Wang, Wenwu
Plumbley, Mark D.
Phan, Huy
Benetos, Emmanouil
author_facet Liang, Jinhua
Zhang, Huan
Liu, Haohe
Cao, Yin
Kong, Qiuqiang
Liu, Xubo
Wang, Wenwu
Plumbley, Mark D.
Phan, Huy
Benetos, Emmanouil
contents We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing. Specifically, WavCraft describes the content of raw audio materials in natural language and prompts the LLM conditioned on audio descriptions and user requests. WavCraft leverages the in-context learning ability of the LLM to decomposes users' instructions into several tasks and tackle each task collaboratively with the particular module. Through task decomposition along with a set of task-specific models, WavCraft follows the input instruction to create or edit audio content with more details and rationales, facilitating user control. In addition, WavCraft is able to cooperate with users via dialogue interaction and even produce the audio content without explicit user commands. Experiments demonstrate that WavCraft yields a better performance than existing methods, especially when adjusting the local regions of audio clips. Moreover, WavCraft can follow complex instructions to edit and create audio content on the top of input recordings, facilitating audio producers in a broader range of applications. Our implementation and demos are available at this https://github.com/JinhuaLiang/WavCraft.
format Preprint
id arxiv_https___arxiv_org_abs_2403_09527
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WavCraft: Audio Editing and Generation with Large Language Models
Liang, Jinhua
Zhang, Huan
Liu, Haohe
Cao, Yin
Kong, Qiuqiang
Liu, Xubo
Wang, Wenwu
Plumbley, Mark D.
Phan, Huy
Benetos, Emmanouil
Audio and Speech Processing
We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing. Specifically, WavCraft describes the content of raw audio materials in natural language and prompts the LLM conditioned on audio descriptions and user requests. WavCraft leverages the in-context learning ability of the LLM to decomposes users' instructions into several tasks and tackle each task collaboratively with the particular module. Through task decomposition along with a set of task-specific models, WavCraft follows the input instruction to create or edit audio content with more details and rationales, facilitating user control. In addition, WavCraft is able to cooperate with users via dialogue interaction and even produce the audio content without explicit user commands. Experiments demonstrate that WavCraft yields a better performance than existing methods, especially when adjusting the local regions of audio clips. Moreover, WavCraft can follow complex instructions to edit and create audio content on the top of input recordings, facilitating audio producers in a broader range of applications. Our implementation and demos are available at this https://github.com/JinhuaLiang/WavCraft.
title WavCraft: Audio Editing and Generation with Large Language Models
topic Audio and Speech Processing
url https://arxiv.org/abs/2403.09527