In the context of three problem areas identified as critical for the future development of the Internet, WebFAQ aimed at addressing the problem of the analysis and representation of the information content. More specifically, the project concentrated on the access to information contained in very large, unstructured, heterogeneous repositories, on multimodal presentation of information, and on the assessment of the quality of information.
Today's task: model compression!!
🎯 Goal: Compress a large, general-purpose multimodal model, making speech translation more efficient ⚡️, deployable 📲, and sustainable ♻️, while preserving translation quality ⭐️
#AI #SpeechTech #ModelCompression #LLMcompression
First up, a new task for 2025:
*Instruction-following for speech processing!*
Explore instruction-following for speech ⇨
Integrate speech foundation models with LLMs across tasks such as speech translation, recognition, summarization, and QA.
🔗:
📢Workshop gratuito 05/02: “Lo stato dell'arte nelle tecnologie per il riconoscimento del parlato.”
Diretta YouTube: https://www.youtube.com/live/i4x7w8fIIXo?si=wYvvrO3-MSh7Yik4
Registrazione: https://www.eventbrite.com/e/biglietti-lo-stato-dellarte-nelle-tecnologie-per-il-riconoscimento-del-parlato-1109098797359?aff=oddtdtcreator
I'm happy to share that our paper "Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison" has been accepted at @naacl @naaclmeeting 2025! #NAACL2025
@Lam19Tk @mgaido91 👏
📃 Preprint:
⏰ Code will be released soon
#NLProc #Speech
