---
title: "Discussion on \"Why Reference Audio Gets Contaminated by Noise in Masked Diffusion TTS\" | Hashnode"
description: "Discussion on \"Why Reference Audio Gets Contaminated by Noise in Masked Diffusion TTS\". Why Reference Audio Gets Contaminated by Noise in Masked Diffusion TTS\n\nThe structural problem with bidirectional self-attention in voice cloning"
url: "https://hashnode.com/posts/why-reference-audio-gets-contaminated-by-noise-in-masked-diffusion-tts/6a366b6e79bb6ff87690fae7"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Why Reference Audio Gets Contaminated by Noise in Masked Diffusion TTS](https://voxflash.hashnode.dev/why-reference-audio-gets-contaminated-by-noise-in-masked-diffusion-tts?utm_source=hashnode&utm_medium=feed)

Why Reference Audio Gets Contaminated by Noise in Masked Diffusion TTS The structural problem with bidirectional self-attention in voice cloning

Jun 20 · 8 min read · voxflash.hashnode.dev  
Read the article

-   [#tts](https://hashnode.com/tag/tts)
-   [#text-to-speech](https://hashnode.com/tag/text-to-speech)
-   [#speechsynthesis](https://hashnode.com/tag/speechsynthesis)
-   [#voice-cloning](https://hashnode.com/tag/voice-cloning)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)

## Written by

[berlin Isaiah](https://hashnode.com/@berlinisaiah)

@berlinisaiah

  
[View profile](https://hashnode.com/@berlinisaiah)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
