Saved in:
Bibliographic Details
Main Authors: Belinchon, Hugo Garrido-Lestache, Mulugeta, Helina, Haile, Adam
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.17608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916228152426496
author Belinchon, Hugo Garrido-Lestache
Mulugeta, Helina
Haile, Adam
author_facet Belinchon, Hugo Garrido-Lestache
Mulugeta, Helina
Haile, Adam
contents Generating audio from a video's visual context has multiple practical applications in improving how we interact with audio-visual media - for example, enhancing CCTV footage analysis, restoring historical videos (e.g., silent movies), and improving video generation models. We propose a novel method to generate audio from video using a sequence-to-sequence model, improving on prior work that used CNNs and WaveNet and faced sound diversity and generalization challenges. Our approach employs a 3D Vector Quantized Variational Autoencoder (VQ-VAE) to capture the video's spatial and temporal structures, decoding with a custom audio decoder for a broader range of sounds. Trained on the Youtube8M dataset segment, focusing on specific domains, our model aims to enhance applications like CCTV footage analysis, silent movie restoration, and video generation models.
format Preprint
id arxiv_https___arxiv_org_abs_2404_17608
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Synthesizing Audio from Silent Video using Sequence to Sequence Modeling
Belinchon, Hugo Garrido-Lestache
Mulugeta, Helina
Haile, Adam
Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
Generating audio from a video's visual context has multiple practical applications in improving how we interact with audio-visual media - for example, enhancing CCTV footage analysis, restoring historical videos (e.g., silent movies), and improving video generation models. We propose a novel method to generate audio from video using a sequence-to-sequence model, improving on prior work that used CNNs and WaveNet and faced sound diversity and generalization challenges. Our approach employs a 3D Vector Quantized Variational Autoencoder (VQ-VAE) to capture the video's spatial and temporal structures, decoding with a custom audio decoder for a broader range of sounds. Trained on the Youtube8M dataset segment, focusing on specific domains, our model aims to enhance applications like CCTV footage analysis, silent movie restoration, and video generation models.
title Synthesizing Audio from Silent Video using Sequence to Sequence Modeling
topic Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2404.17608