MBr解码在语音识别中优于传统束搜索，提升准确率。
Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition
- 用采样式最小贝叶斯风险解码替代束搜索
- 在英日语语音识别任务中多数场景准确率更高
- 适合对精度要求高的离线语音识别应用
近期研究表明，基于采样的最小贝叶斯风险（MBR）解码在文本到文本生成任务中优于束搜索，如机器翻译、文本摘要和图像字幕生成。然而，束搜索仍是当前语音转文字任务（如自动语音识别，ASR）和语音翻译（ST）的主流方法。鉴于MBR在文本生成中的有效性，我们评估了其在英语和日语的ASR与ST任务中的表现，使用Whisper及其衍生模型。实验结果显示，在大多数测试设置中，MBR解码的准确率显著高于束搜索。结果表明，MBR解码是高精度离线语音识别与语音翻译任务的有前景方法。代码已开源：https://github.com/CyberAgentAILab/mbr-for-asr
原文摘要 · Abstract (English)
Recent work has shown that sample-based Minimum Bayes Risk (MBR) decoding outperforms beam search in text-to-text generation tasks, such as machine translation, text summarization, and image captioning. On the other hand, beam search is the current practice for speech-to-text tasks such as automatic speech recognition (ASR) and Speech Translation (ST). Given that MBR decoding is effective in text-to-text generation tasks, it is reasonable to expect it to also be effective for speech-to-text tasks. In this paper, we evaluate MBR decoding for ASR and ST tasks on English and Japanese using Whisper and its derivative models. We observe that the accuracy of MBR decoding outperforms that of beam search in most of the experimental settings we have evaluated. The results show that MBR decoding is a promising method for offline ASR and ST tasks that require high accuracy. The code is available at https://github.com/CyberAgentAILab/mbr-for-asr
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。