The scientific and technological objectives of QALL-ME pursued three crucial directions: multilingual open domain QA, user-driven and context-aware QA, and learning technologies for QA. The specific research objectives of the project included state-of-art advancements in the complexity of the questions handled by the system(e.g. how questions); the development of a web-based architecture for cross-language QA (i.e. question in one language, answer in a different language); the realization of real-time QA systems for concrete applications; the integration of the temporal and spatial context both for question interpretation and for answer extraction; the development of a robust framework for applying minimally supervised machine learning algorithms to QA tasks; and the integration of mature technologies for automatic speech recognition within the open domain question answering framework.
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