AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

Dmitrii Korzh, Dmitrii Tarasov, Artyom Iudin, Elvir Karimov, Matvey Skripkin, Nikita Kuzmin, Andrey Kuznetsov, Oleg Rogov, Ivan Oseledets

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Speech and audio language models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on human audio instead of TTS-only audio (ablation)Qwen2.5 post-correction · S2L-sentences (human test, sentence CER)CER: 33.74 -> 29.18 (Q-0.5B)Improved
add 400k MathBridge TTS samples to training (Mix-full) (ablation)Qwen2.5-0.5B post-correction · S2L-equations (English test, mix)CER: 32.33 -> 27.21Improved
add 400k English TTS samples (ablation)post-correction models · S2L-equations (Russian test)CERHurt
add Russian data to training (ablation)Qwen2.5-0.5B (human train) · S2L-equations (English human test)CER: 35.01 -> 33.94 (0.5B); 27.57 -> 28.85 (1.5B)Mixed
use math-specialized Qwen2.5-Math-1.5B instead of Qwen2.5-1.5B (ablation)post-correction · S2L-equations (English)CERNo clear effect
add LaTeX symbols as extra tokens to tokenizer (ablation)post-correction LLMs · S2L-equationsCERNo clear effect
normalize LaTeX with AST-based KaTeX forkevaluation of S2L-equations · S2L-equationsCER: reduced CER by ~1%Improved
use end-to-end SALMONN audio-LLM instead of ASR post-correctionS2L-equations · S2L-equations (English test, mix)CER: 25.69 -> 17.50Improved
use few-shot prompting instead of fine-tuning (ablation)Qwen2.5 models · S2L-sentencesEquation CER: 43.75 -> 57.91 (Q-7B, 5-shot)Hurt
scale post-correction LLM to 7B with LoRA (ablation)Qwen2.5 post-correction · S2L-equations (English)CERNo clear effect
scale Qwen2.5 to 7B with LoRA (ablation)Qwen2.5 post-correction · S2L-sentencesEquation CER: 54.07 -> 43.75 (0.5B Mix vs 7B Mix)Improved
add TTS audio to human audio for training (ablation)SALMONN-13B · S2L-sentences (human test)Equation CER: 41.53 -> 39.68Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy