HackerPapers

arXiv:2008.04259eess.AS

A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

Jean-Marc Valin, Umut Isik, Neerad Phansalkar, Ritwik Giri, Karim Helwani, Arvindh Krishnaswamy

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time Fourier transform (STFT) domain, resulting in a high computational complexity. In this work, we propose PercepNet, an efficient approach that relies on human perception of speech by focusing on the spectral envelope and on the periodicity of the speech. We demonstrate high-quality, real-time enhancement of fullband (48 kHz) speech with less than 5% of a CPU core.

arXiv comments
Proc. INTERSPEECH 2020, 5 pages
Journal reference
DOI
Subjects
eess.ASAudio and Speech Processing

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jan 2021 to Jan 2021.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Show HN: Unclack – a macOS app that mutes your microphone while you type 1 comment

    • It's worth noting that RNNoise uses way less resources than RTX Voice and doesn't require a GPU. There's a new paper by Jean-Marc Valin (RNNoise author) about a new and improved version PercepNet[0] that's also very light on resource usage, but it's currently lacking an open…

      lawlView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.