Dialog enhancement (DE) is a feature that allows a listener to increase the level of dialog in a content item relative to backgrounds. DE is “unguided” if only the finished mix is available, meaning that a DE system must estimate the dialog. Spatio-Level Filtering (SLF) is a source separation technology that, when combined with dialog classification, allows for high-quality unguided DE for typical entertainment content in a stereo or higher channel count format. SLF exploits spatial and level information and requires little lookahead, memory, computation and training data. To evaluate results, we conduct two subjective listening experiments which indicate favorable performance.

Authors: Master, Aaron S.; Lu, Lie; Lehtonen, Heidi-Maria; Mundt, Harald; Purnhagen, Heiko; Darcy, Dan
Affiliations: Dolby Laboratories, Inc, San Francisco, CA, USA; Dolby Sweden AB, Stockholm, Sweden; Dolby Germany GmbH, Nürnberg, Germany(See document for exact affiliation information.)
AES Convention: 149 (October 2020) Paper Number: 10427
Publication Date: October 22, 2020 Import into BibTeX
Subject: Audio Processing
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=20964

Download Now (780 KB)

This paper is Open Access which means you can download it for free.

Learn more about the AES E-Library

E-Library Location:   /conv/149/10427.pdf

Start a discussion about this paper!