基於RNN Transducer端到端語音識別的最小貝葉斯風險訓練 | 論文解讀

{"type":"doc","content":[{"type":"heading","attrs":{"align":null,"level":2},"content":[{"type":"text","text":"一、概述"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"端到端語音識別技術將語音識別系統中的各個組件整合至同一個神經網絡框架中，與傳統語音識別系統相比具有建模簡潔，賦能組件之間聯合優化以及系統佔用空間小等優點，近幾年逐漸成爲語音識別領域裏最重要的研究方向之一。現有的端到端語音識別系統主要包括基於 Connnectionist Temporal Classification (CTC)，基於 Sequence-to-sequence(Seq2Seq) 以及基於 RNN Transducer (RNNT) 三類系統。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}}]}