CMU's IWSLT 2025 Simultaneous Speech Translation System
Not on the map. Why?
Abstract (arXiv)
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 curated 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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 16 Jun 2025.
Builds on
15 of 24 references.
References · 15
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
- 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
- 2020Language-agnostic BERT Sentence Embeddingcited by 627
- 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
- 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
- 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 156
- 2019Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debatescited by 114
- 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 76
- 2023Speech Translation with Large Language Models: An Industrial Practicecited by 28
3 more
- 2024StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selectioncited by 19
- 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
- 2025InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Modelcited by 8
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.