原帖引用 · AI 翻译
Hugging Face 上的公开测试集：https://t.co/efBJYzdtGZ
排行榜已上线：https://t.co/jqvvYGtTeq
语音识别评测必须在语音智能体实际工作的场景中进行测试，也就是两个人之间的电话通话。
Voice Arena 的新基准测试使用在普通手机上、真实房间里、有真实背景声音的通话，测试语音转文字模型。
两名说话者让模型的任务难得多。人们会同时说话、打断对方，插入简短的“嗯”和“好的”等回应，而电话线路会压缩音频。客服或销售智能体每天都要应对这些情况。
原文
Speech recognition evalualtion must test where voice agents actually work, which is phone calls between two people. Voice Arena’s new benchmark tests speech-to-text models on real calls made on everyday phones, in real rooms, with real background sound. Two speakers make the job much harder for the model. People talk over each other, interrupt, drop in short “yeah” and “okay” replies, and the phone line compresses the audio. A support or sales agent deals with all of this every day.
第 3/15 项发布：推出 @voicearena_ai 的语音识别基准测试。
一个涵盖每种语言、每种语音识别用例的基准测试。使用真实对话进行测试。
数据集 1 已上线：Monsoon Conversational ASR Test Set，包含 5 种语言的双人对话。
排行榜和公开测试集均可在 Voice Arena 查看。
原文
Drop 3/15: Introducing the Speech Recognition Benchmark on @voicearena_ai. One benchmark for every use case of speech recognition, in every language. Tested on real conversations. Dataset 1 is live: the Monsoon Conversational ASR Test Set, two-person conversations in 5 languages. Leaderboard and public test sets at Voice Arena.