# Instituto de Telecomunica\\c{c}\\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning

Source: [Instituto de Telecomunica\\c{c}\\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning](<https://www.sota2.com/research/paper/68fa79921e209131cea7e53f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:01:45.766Z

Authors: Giuseppe Attanasio, Sonal Sannigrahi, Ben Peters, Andr\\'e F. T. Martins

Published: 2025-06-20T14:17:42.000Z

## Abstract

This paper presents the IT-IST submission to the IWSLT 2025 Shared Task on Instruction Following Speech Processing. We submit results for the Short Track, i.e., speech recognition, translation, and spoken question answering. Our model is a unified speech-to-text model that integrates a pre-trained continuous speech encoder and text decoder through a first phase of modality alignment and a second phase of instruction fine-tuning. Crucially, we focus on using small-scale language model backbones (\< 2B) and restrict to high-quality, CC-BY data along with synthetic data generation to supplement existing resources.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.17019>)

[PDF](<https://arxiv.org/pdf/2506.17019.pdf>)
