From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLM

Kshitij Ambilduke, Ben Peters, Sonal Sannigrahi, Anil Keshwani, Tsz Kin Lam, Bruno Martins, Andre Martins, Marcely Zanon Boito


Abstract
We introduce Spire, a speech-augmented language model (LM) capable of both translating and transcribing speech input from English into 10 other languages as well as translating text input in both language directions. Spire integrates the speech modality into an existing multilingual LM via speech discretization and continued pre-training using only 42.5 K hours of speech. In particular, we adopt the pretraining framework of multilingual LMs and treat discretized speech input as an additional translation language. This approach not only equips the model with speech capabilities, but also preserves its strong text-based performance. We achieve this using significantly less data than existing speech LMs, demonstrating that discretized speech input integration as an additional language is feasible during LM adaptation. We make our code and models available to the community.
Anthology ID:
2025.findings-emnlp.1071
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19658–19673
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1071/
DOI:
Bibkey:
Cite (ACL):
Kshitij Ambilduke, Ben Peters, Sonal Sannigrahi, Anil Keshwani, Tsz Kin Lam, Bruno Martins, Andre Martins, and Marcely Zanon Boito. 2025. From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLM. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 19658–19673, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLM (Ambilduke et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1071.pdf
Checklist:
 2025.findings-emnlp.1071.checklist.pdf