# BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System

arXiv: https://arxiv.org/abs/2505.24016 · HTML: https://mlsanity.com/paper/2505.24016/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 9 of 9)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection](https://mlsanity.com/paper/2406.06097/) (2024)
- [Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation](https://mlsanity.com/paper/2405.10443/) (2024)
- [Does Joint Training Really Help Cascaded Speech Translation?](https://mlsanity.com/paper/2210.13700/) (2022)
- [Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases](https://mlsanity.com/paper/2402.00632/) (2024)

## Built on by (most cited first, 1 of 1)

- [Streaming Translation and Transcription Through Speech-to-Text Causal Alignment](https://mlsanity.com/paper/2603.11578/) (2026)

## Abstract (arXiv)

This paper discusses the construction, fine-tuning, and deployment of BeaverTalk, a cascaded system for speech-to-text translation as part of the IWSLT 2025 simultaneous translation task. The system architecture employs a VAD segmenter for breaking a speech stream into segments, Whisper Large V2 for automatic speech recognition (ASR), and Gemma 3 12B for simultaneous translation. Regarding the simultaneous translation LLM, it is fine-tuned via low-rank adaptors (LoRAs) for a conversational prompting strategy that leverages a single prior-sentence memory bank from the source language as context. The cascaded system participated in the EnglishrightarrowGerman and EnglishrightarrowChinese language directions for both the low and high latency regimes. In particular, on the EnglishrightarrowGerman task, the system achieves a BLEU of 24.64 and 27.83 at a StreamLAAL of 1837.86 and 3343.73, respectively. Then, on the EnglishrightarrowChinese task, the system achieves a BLEU of 34.07 and 37.23 at a StreamLAAL of 2216.99 and 3521.35, respectively.