lattice-free maximum mutual information-based acoustic models with sequence-level Kullback-Leibler divergence” (*2) S. Karita, et al., “A COMPARATIVE STUDY ON TRANSFORMER VS RNN IN SPEECH APPLICATIONS” End-to-End型により誤りが半減 0 2 4 6 8 10 E1 E2 E3 ⽇本語話し⾔葉コーパス(CSJ)に対する認識誤り率 (%) DNN-HMM End-to-End