From d5567391cb0b1149c9880d4b2c53b44278870161 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=EC=9D=B4=EC=A4=80=ED=98=81=28Junhyeok=20Lee=29?=
 <junjun3518@gmail.com>
Date: Tue, 9 Jul 2024 15:01:19 +0900
Subject: [PATCH] Update publications.mdx

---
 src/pages/publications.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/pages/publications.mdx b/src/pages/publications.mdx
index 2897391..3a87144 100644
--- a/src/pages/publications.mdx
+++ b/src/pages/publications.mdx
@@ -17,7 +17,7 @@ import * as features from '@site/src/components/PublicationFeatures';
         <li>
             <features.ConferenceItem conference="Interspeech"/>
             <features.PaperTitle paperLink="https://arxiv.org/abs/2406.06111" title="JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis"/>
-            <features.AuthorItem authors={["Hyunjae Cho", "Junhyeok Lee", "Wonbin Jung"]} numFirstAuthor={1} isBrainTeam={[true, true, true]}/>
+            <features.AuthorItem authors={["Hyunjae Cho", "Junhyeok Lee", "Wonbin Jung"]} numFirstAuthor={2} isBrainTeam={[true, true, true]}/>
             <features.PaperDescription preview="Non-autoregressive GAN-based neural vocoders are widely used due to their fast inference speed and high perceptual quality. "
             description="However, they often suffer from audible artifacts such as tonal artifacts in their generated results. Therefore, we propose JenGAN, a new training strategy that involves stacking shifted low-pass filters to ensure the shift-equivariant property. This method helps prevent aliasing and reduce artifacts while preserving the model structure used during inference. In our experimental evaluation, JenGAN consistently enhances the performance of vocoder models, yielding significantly superior scores across the majority of evaluation metrics."/>
         </li>