AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries

Autor:	Choi, Woosung, Kim, Minseok, Ramírez, Marco A. Martínez, Chung, Jaehwa, Jung, Soonyoung
Rok vydání:	2021
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Machine Learning Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	This paper proposes a neural network that performs audio transformations to user-specified sources (e.g., vocals) of a given audio track according to a given description while preserving other sources not mentioned in the description. Audio Manipulation on a Specific Source (AMSS) is challenging because a sound object (i.e., a waveform sample or frequency bin) is `transparent'; it usually carries information from multiple sources, in contrast to a pixel in an image. To address this challenging problem, we propose AMSS-Net, which extracts latent sources and selectively manipulates them while preserving irrelevant sources. We also propose an evaluation benchmark for several AMSS tasks, and we show that AMSS-Net outperforms baselines on several AMSS tasks via objective metrics and empirical verification. Comment: 10 pages, 8 figures, 3 tables, under reviewing of ACMMM 21
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2104.13553 Zobrazit plný text záznamu View this record from Arxiv