---
title: "GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech — Stuff That Spins"
description: "arXiv:2607.02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language mode…"
	canonical: "https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech"
html: "https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech"
json: "https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech.json"
markdown: "https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-07-07T04:00:00+00:00"
modified: "2026-07-07T06:05:01.194267+00:00"
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://stuffthatspins.com/#organization","name":"Stuff That Spins","url":"https://stuffthatspins.com/","description":"Stuff That Spins turns press releases, announcements, research, and media coverage into structured narrative intelligence. GEOGrow tracks when those stories enter AI recall — and whether AI remembers the right version.","logo":{"@type":"ImageObject","url":"https://stuffthatspins.com/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech#article","headline":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech","description":"arXiv:2607.02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language mode…","datePublished":"2026-07-07T04:00:00+00:00","dateModified":"2026-07-07T06:05:01.194267+00:00","url":"https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"research","author":{"@type":"Organization","name":"arXiv Machine Learning","url":"https://export.arxiv.org/rss/cs.LG"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://arxiv.org/abs/2607.02633","about":[],"mentions":[{"@type":"Organization","name":"arXiv Machine Learning"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech","item":"https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech"}]}]}
---

# GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech

**Source:** Unknown  
**Published:** July 7, 2026  
**Original:** https://arxiv.org/abs/2607.02633  

## On this page

- [Overview](#overview)

<a id="overview"></a>

## Overview

arXiv:2607.02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling. Existing systems reach high intelligibility and naturalness but inherit the ambiguity of text and mispronounce rare proper nouns, loanwords and technical terms. Even phoneme-conditioned models offer no direct acoustic handle for per-word pronunciation. GRAFT controls the pronunciation of a chosen word from a short spoken sample of it

---
*HTML version: https://stuffthatspins.com/spin/graft-grafted-reference-audio-for-fine-grained-pronunciation-in-zero-shot-text-to-speech*