zero-shot paper

src/app/about-event.tsx

@@ -15,6 +15,16 @@ import React from 'react';
 
 
 const EVENT_INFO = [
+
+ {
+   title: "NaturalSpeech 3: Zero-Shot Speech Synthesis \
+with Factorized Codec and Diffusion Models",
+   description: "FACodec is a core component of the advanced text-to-speech (TTS) model NaturalSpeech 3. FACodec converts complex speech waveform into disentangled subspaces representing speech attributes of content, prosody, timbre, and acoustic details and reconstruct high-quality speech waveform from these attributes. FACodec decomposes complex speech into subspaces representing different attributes, thus simplifying the modeling of speech representation. Hf-Demo : https://huggingface.co/spaces/amphion/naturalspeech3_facodec",
+   subTitle: "Zero-Shot Voice Clone / Audio",
+   imageName : "zero-shot.png",
+   paper_links :"https://arxiv.org/pdf/2403.03100.pdf"
+ },
+
   {
   title: "ResAdapter : Domain Consistent Resolution Adapter for Diffusion Models",
   description: "Overview of ResAdapter. Left: Pipeline of ResAdapter. It is based on the frozen model (e.g., SD or SDXL) learns resolution priors from mixed-resolution datasets, which can be integrated into any personalized model to generate multi-resolution images. Right: Architecture comparison between ResAdapter and the vanilla LoRA. ResAdapter is only inserted to downsampler and upsampler, and unfreezes the group normalization of resnet blocks. Page:https://res-adapter.github.io/",