MathReader : Text-to-Speech for Mathematical Documents

1 code implementation • 13 Jan 2025 • Sieun Hyeon, Kyudan Jung, Nam-Joon Kim, Hyun Gon Ryu, Jaeyoung Do

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.

Optical Character Recognition (OCR) Text to Speech

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

1 code implementation • 20 Dec 2024 • Sieun Hyeon, Kyudan Jung, Jaehee Won, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Jaeyoung Do

In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

TeXBLEU: Automatic Metric for Evaluate LaTeX Format

1 code implementation • 10 Sep 2024 • Kyudan Jung, Nam-Joon Kim, Hyongon Ryu, Sieun Hyeon, Seung-jun Lee, Hyeok-jae Lee

LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science.

MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into $LaTeX$ Formulas for Improved Readability

no code implementations • 7 Aug 2024 • Kyudan Jung, Sieun Hyeon, Jeong Youn Kwon, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Jaeyoung Do

Even if we try to solve this using language models, there is no paired data between spoken sentences and LaTeX formulas to train it.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2