The project ATLAS created the technological bridge between cognitive sciences and the most progressive information technologies. The project was patronized by the region of Piedmont and financed by the program of development of innovative services and it gave the possibility to deaf people to look and understand programs of mass media through automatic translation from the Italian written language into the sign language (LIS) which is visualized a virtual actor created by computer animation drawing means. Through these tools the project achieved the aim to give the possibility to deaf people to understand television programs, WEB pages and films reproduced on DVD by the virtual translator personated in time which can be visualized on different types of display from television screen to computer, from mobile phones to PDAs.
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