Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Yu-Ren, Tai, Wen-Kai
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.03244
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913833737519104
author Guo, Yu-Ren
Tai, Wen-Kai
author_facet Guo, Yu-Ren
Tai, Wen-Kai
contents Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing (NLP) and multimodal learning, with successful applications in text generation and speech synthesis, enabling a deeper understanding and generation of multimodal content. In the field of sound effects (SFX) generation, LLMs have been leveraged to orchestrate multiple models for audio synthesis. However, due to the scarcity of annotated datasets, and the complexity of temproal modeling. current SFX generation techniques still fall short in achieving high-fidelity audio. To address these limitations, this paper introduces a novel framework that integrates LLMs with existing sound effect databases, allowing for the retrieval, recombination, and synthesis of audio based on user requirements. By leveraging this approach, we enhance the diversity and quality of generated sound effects while eliminating the need for additional recording costs, offering a flexible and efficient solution for sound design and application.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03244
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SonicRAG : High Fidelity Sound Effects Synthesis Based on Retrival Augmented Generation
Guo, Yu-Ren
Tai, Wen-Kai
Sound
Audio and Speech Processing
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing (NLP) and multimodal learning, with successful applications in text generation and speech synthesis, enabling a deeper understanding and generation of multimodal content. In the field of sound effects (SFX) generation, LLMs have been leveraged to orchestrate multiple models for audio synthesis. However, due to the scarcity of annotated datasets, and the complexity of temproal modeling. current SFX generation techniques still fall short in achieving high-fidelity audio. To address these limitations, this paper introduces a novel framework that integrates LLMs with existing sound effect databases, allowing for the retrieval, recombination, and synthesis of audio based on user requirements. By leveraging this approach, we enhance the diversity and quality of generated sound effects while eliminating the need for additional recording costs, offering a flexible and efficient solution for sound design and application.
title SonicRAG : High Fidelity Sound Effects Synthesis Based on Retrival Augmented Generation
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.03244