MathReader : Text-to-Speech for Mathematical Documents
Not on the map. Why?
Abstract (arXiv)
TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions. This is because most modern academic papers are written in LaTeX, and when LaTeX formulas are compiled, they are rendered as distinctive text forms within the document. However, traditional TTS document readers output only the text as it is recognized, without considering the mathematical meaning of the formulas. To address this issue, we propose MathReader, which effectively integrates OCR, a fine-tuned T5 model, and TTS. MathReader demonstrated a lower Word Error Rate (WER) than existing TTS document readers, such as Microsoft Edge and Adobe Acrobat, when processing documents containing mathematical formulas. MathReader reduced the WER from 0.510 to 0.281 compared to Microsoft Edge, and from 0.617 to 0.281 compared to Adobe Acrobat. This will significantly contribute to alleviating the inconvenience faced by users who want to listen to documents, especially those who are visually impaired. The code is available at https://github.com/hyeonsieun/MathReader.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 13 of its 28 references that are in the map. First posted on arXiv 13 Jan 2025.
Builds on
13 of 28 references.
References · 13
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2023GPT-4 Technical Reportcited by 18,132
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
- 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
- 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
- 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 233
- 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
- 2023VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Designcited by 25
- 2023UPOCR: Towards Unified Pixel-Level OCR Interfacecited by 12
- 2024LATEX-GCL: Large Language Models (LLMs)-Based Data Augmentation for Text-Attributed Graph Contrastive Learningcited by 4
Built on by
Citing papers per year: 2025: 3.
3 papers.