Application of Hybrid CTC/2D-Attention End-to-End Model in Speech Recognition during the COVID-19 Pandemic

In end-to-end speech recognition task, the goal is through a network, the input ㉠ 1,…, , calculate all output tags sequence ㉠ 1,…, corresponding probability, usually ≤ , ∈ , is a finite character set, the final output is one of the biggest probability tags sequence, namely