@inproceedings{ouyang-etal-2025-cmus,
title = "{CMU}{'}s {IWSLT} 2025 Simultaneous Speech Translation System",
author = "Ouyang, Siqi and
Xu, Xi and
Li, Lei",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Anastasopoulos, Antonis",
booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/landing_page/2025.iwslt-1.31/",
pages = "309--314",
ISBN = "979-8-89176-272-5",
abstract = "This paper presents CMU{'}s submission to the IWSLT 2025 Simultaneous Speech Translation (SST) task for translating unsegmented English speech into Chinese and German text in a streaming manner. Our end-to-end speech-to-text system integrates a chunkwise causal Wav2Vec 2.0 speech encoder, an adapter, and the Qwen2.5-7B-Instruct as the decoder. We use a two-stage simultaneous training procedure on robust speech segments synthesized from LibriSpeech, CommonVoice, and VoxPopuli datasets, utilizing standard cross-entropy loss. Our model supports adjustable latency through a configurable latency multiplier. Experimental results demonstrate that our system achieves 44.3 BLEU for English-to-Chinese and 25.1 BLEU for English-to-German translations on the ACL60/60 development set, with computation-aware latencies of 2.7 seconds and 2.3 seconds, and theoretical latencies of 2.2 and 1.7 seconds, respectively."
}
Markdown (Informal)
[CMU’s IWSLT 2025 Simultaneous Speech Translation System](https://preview.aclanthology.org/landing_page/2025.iwslt-1.31/) (Ouyang et al., IWSLT 2025)
ACL
- Siqi Ouyang, Xi Xu, and Lei Li. 2025. CMU’s IWSLT 2025 Simultaneous Speech Translation System. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 309–314, Vienna, Austria (in-person and online). Association for Computational Linguistics.