---
title: "Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs — Stuff That Spins"
description: "arXiv:2607.06831v1 Announce Type: new Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide s…"
	canonical: "https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms"
html: "https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms"
json: "https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms.json"
markdown: "https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-07-09T04:00:00+00:00"
modified: "2026-07-09T06:03:46.573638+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/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms#article","headline":"Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs","description":"arXiv:2607.06831v1 Announce Type: new Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide s…","datePublished":"2026-07-09T04:00:00+00:00","dateModified":"2026-07-09T06:03:46.573638+00:00","url":"https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"research","author":{"@type":"Organization","name":"arXiv Computation and Language","url":"https://export.arxiv.org/rss/cs.CL"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://arxiv.org/abs/2607.06831","about":[],"mentions":[{"@type":"Organization","name":"arXiv Computation and Language"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs","item":"https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms"}]}]}
---

# Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs

**Source:** Unknown  
**Published:** July 9, 2026  
**Original:** https://arxiv.org/abs/2607.06831  

## On this page

- [Overview](#overview)

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

## Overview

arXiv:2607.06831v1 Announce Type: new Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide such an alignment directly and others do not. Connectionist temporal classification (CTC) and transducer models have an alignment by construction, whereas attention-based encoder-decoders (AED) and speech large language models (LLMs) do not, and their word timings are usually read off the attention weights instead. All of these signals live

---
*HTML version: https://stuffthatspins.com/spin/gradient-based-speech-to-text-alignment-for-any-asr-model-from-ctc-to-speech-llms*