MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula

TL;DR

MathSpeech is a pipeline that combines small language models with ASR to accurately convert spoken mathematical expressions into LaTeX, improving clarity and correctness over existing methods.

Contribution

We propose MathSpeech, a novel approach using small language models to enhance mathematical speech-to-formula conversion accuracy, rivaling large models like GPT-4o.

Findings

Reduced CER from 0.390 to 0.298

Achieved higher ROUGE and BLEU scores than GPT-4o

Demonstrated effective LaTeX generation with small models

Abstract

In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally. However, reading mathematical expressions aloud without accompanying visuals can significantly hinder comprehension, especially for those who are hearing-impaired or rely on subtitles due to language barriers. For instance, when a presenter reads Euler's Formula, current Automatic Speech Recognition (ASR) models often produce a verbose and error-prone textual description (e.g., e to the power of i x equals cosine of x plus i $\textit{side}$ of x), instead of the concise $\LaTeX{}$ format (i.e., $ e^{ix} = \cos(x) + i\sin(x) $), which hampers clear understanding and communication. To address this issue, we introduce MathSpeech, a novel pipeline that integrates ASR models with small Language Models (sLMs) to correct errors in mathematical expressions and accurately convert spoken expressions into structured $\LaTeX{}$ representations. Evaluated on a new dataset derived from lecture recordings, MathSpeech demonstrates $\LaTeX{}$ generation capabilities comparable to leading commercial Large Language Models (LLMs), while leveraging fine-tuned small language models of only 120M parameters. Specifically, in terms of CER, BLEU, and ROUGE scores for $\LaTeX{}$ translation, MathSpeech demonstrated significantly superior capabilities compared to GPT-4o. We observed a decrease in CER from 0.390 to 0.298, and higher ROUGE/BLEU scores compared to GPT-4o.