From 1626d0a2f95b6ebcbe03a49bbef9318392ad4ff3 Mon Sep 17 00:00:00 2001 From: Rory Lu Date: Sun, 8 Sep 2024 14:57:29 +0800 Subject: [PATCH] Update README.md --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 9dfc5d3d..538126a7 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,8 @@ # Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement ### Ye-Xin Lu, Yang Ai, Zhen-Hua Ling In our [paper](https://arxiv.org/abs/2305.13686), we proposed MP-SENet: a TF-domain monaural SE model with parallel magnitude and phase spectra denoising. -A long-version MP-SENet is available on [arxiv](https://arxiv.org/abs/2308.08926) now.
+A long-version MP-SENet is available on [arxiv](https://arxiv.org/abs/2308.08926) now. +Audio samples can be found at the [demo website](http://yxlu-0102.github.io/MP-SENet).
We provide our implementation as open source in this repository. **Abstract:** @@ -17,8 +18,6 @@ Experimental results demonstrate that our proposed MP-SENet achieves state-of-th Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech. Remarkably, for the speech denoising task, the proposed MP-SENet yields a PESQ of **3.60** on the VoiceBank+DEMAND dataset and **3.62** on the DNS challenge dataset. -Audio samples can be found [here](http://yxlu-0102.github.io/MP-SENet). - ## Pre-requisites 1. Python >= 3.6. 2. Clone this repository.