7 papers
Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models
Jinwoo Jeon, GyuYeop Do, Yubin Lim +4
Large-scale vision-language models (VLM) such as CLIP enable strong open-vocabulary reasoning, yet deploying these capabilities on resource-constrained edge devices remains challen…
Whisfusion: Parallel ASR Decoding with Masked Diffusion
Taeyoun Kwon, Junhyuk Ahn, Taegeun Yun +7
Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length. A natural a…
MathReader : Text-to-Speech for Mathematical Documents
Sieun Hyeon, Kyudan Jung, Nam-Joon Kim +2
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 som…
MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula
Sieun Hyeon, Kyudan Jung, Jaehee Won +4
In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally. However, rea…
TeXBLEU: Automatic Metric for Evaluate LaTeX Format
Kyudan Jung, Nam-Joon Kim, Hyongon Ryu +3
LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science. Although the use of mathematical expressions in LaTeX format…
MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into Formulas for Improved Readability
Kyudan Jung, Sieun Hyeon, Jeong Youn Kwon +4
Improving the readability of mathematical expressions in text-based document such as subtitle of mathematical video, is an significant task. To achieve this, mathematical expressio…
Enhancing ASR Performance through OCR Word Frequency Analysis: Theoretical Foundations
Kyudan Jung, Nam-Joon Kim, Hyun Gon Ryu +1
As the interest in large language models grows, the importance of accuracy in automatic speech recognition has become more pronounced. This is especially true for lectures that inc…