Voice Arena 推出语音识别基准，用真实对话测试 ASR
Voice Arena 发了个用真实对话测语音识别的基准，语气词、说一半断掉都算分，比脚本台词的测试靠谱，5 种语言数据集已上线。
Voice Arena 上线 Speech Recognition Benchmark，覆盖语音识别的各类使用场景和多种语言。首个数据集为 Monsoon Conversational ASR Test Set，包含 5 种语言的双人真实对话。与传统使用脚本台词的评测不同，该基准纳入了语气词、口误和说到一半停顿等真实语音特征。排行榜和公开测试集已在 Voice Arena 平台发布。
Real conversations have filler words, false starts and people trailing off mid-sentence. Nice to see ASR scored on that instead of scripted lines. Shobhit Banga @shobhitbanga 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. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 693 ⚡
