IEEE

Wav2Seq: Pre-Training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages

Abstract: We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, ...
GitHub

Rust VBScript lexer and parser

On October 2023 Microsoft deprecated VBScript. A timeline is available at the Windows IT Pro Blog. However, there are still many legacy systems that use VBScript. This project aims to provide a lexer, ...
The Guardian

‘Reimagining matter’: Nobel laureate invents machine that harvests water from dry air

Omar Yaghi’s invention uses ambient thermal energy and can generate up to 1,000 litres of clean water every day A Nobel laureate’s environmentally friendly invention that provides clean water if ...
IEEE

Advancing Clinical Text Summarization through Extractive Methods using BERT-Based Models on the NBME Dataset

Abstract: Medical notes contains a vast amount of healthcare information. NLP techniques are essential for extracting the most relevant insights from abundance data, enabling healthcare professionals ...