The IT-IST IWSLT 2025 submission shows that a 1.5B language model with a speech encoder can do reasonable ASR after alignment, but struggles with ST and SQA.
In 2022 IEEE Spoken Language Technology Workshop (SLT), pages 798–805
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Instituto de Telecomunica\c{c}\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning
The IT-IST IWSLT 2025 submission shows that a 1.5B language model with a speech encoder can do reasonable ASR after alignment, but struggles with ST and SQA.