VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jung, Jaemin, Ahn, Junseok, Jung, Chaeyoung, Nguyen, Tan Dat, Jang, Youngjoon, Chung, Joon Son
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916543498027008
author Jung, Jaemin
Ahn, Junseok
Jung, Chaeyoung
Nguyen, Tan Dat
Jang, Youngjoon
Chung, Joon Son
author_facet Jung, Jaemin
Ahn, Junseok
Jung, Chaeyoung
Nguyen, Tan Dat
Jang, Youngjoon
Chung, Joon Son
contents 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 conditions remains a significant and underexplored challenge in the field. To address this, we present a novel audio generation pipeline named VoiceDiT. This pipeline includes three key components: (1) the creation of a large-scale synthetic speech dataset for pre-training and a refined real-world speech dataset for fine-tuning, (2) the Dual-DiT, a model designed to efficiently preserve aligned speech information while accurately reflecting environmental conditions, and (3) a diffusion-based Image-to-Audio Translator that allows the model to bridge the gap between audio and image, facilitating the generation of environmental sound that aligns with the multi-modal prompts. Extensive experimental results demonstrate that VoiceDiT outperforms previous models on real-world datasets, showcasing significant improvements in both audio quality and modality integration.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19259
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
Jung, Jaemin
Ahn, Junseok
Jung, Chaeyoung
Nguyen, Tan Dat
Jang, Youngjoon
Chung, Joon Son
Audio and Speech Processing
Sound
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 conditions remains a significant and underexplored challenge in the field. To address this, we present a novel audio generation pipeline named VoiceDiT. This pipeline includes three key components: (1) the creation of a large-scale synthetic speech dataset for pre-training and a refined real-world speech dataset for fine-tuning, (2) the Dual-DiT, a model designed to efficiently preserve aligned speech information while accurately reflecting environmental conditions, and (3) a diffusion-based Image-to-Audio Translator that allows the model to bridge the gap between audio and image, facilitating the generation of environmental sound that aligns with the multi-modal prompts. Extensive experimental results demonstrate that VoiceDiT outperforms previous models on real-world datasets, showcasing significant improvements in both audio quality and modality integration.
title VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2412.19259