CMU提出端到端流式语音翻译系统，支持可调延迟，中英德语翻译效果佳。
CMU's IWSLT 2025 Simultaneous Speech Translation System
- 采用分块因果Wav2Vec 2.0编码器+适配器+Qwen2.5-7B解码器的端到端架构
- 中英翻译44.3 BLEU，德英翻译25.1 BLEU，理论延迟低至1.7秒
- 支持可配置延迟乘子，适合实时会议、字幕等低延迟场景
本文介绍卡内基梅隆大学在IWSLT 2025流式语音翻译任务中的提交方案，实现未分段英语语音到中文和德语文本的流式翻译。系统为端到端语音转文本架构，包含分块因果Wav2Vec 2.0语音编码器、适配器以及Qwen2.5-7B-Instruct作为解码器。在从LibriSpeech、CommonVoice和VoxPopuli数据集筛选的鲁棒语音片段上，采用两阶段流式训练，使用标准交叉熵损失。模型通过可配置延迟乘子支持可调延迟。实验结果表明，在ACL60/60开发集上，中英翻译达到44.3 BLEU，德英翻译达25.1 BLEU，计算感知延迟分别为2.7秒和2.3秒，理论延迟分别为2.2秒和1.7秒。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。