Skip to main content

Table 5 Parameter reduction by soft target training

From: Wise teachers train better DNN acoustic models

Network

# of Params

Data

Hub5’00-SWB

RT03S-FSH

6 ×2048 (hard align., sMBR)

30.4 mil.

110 h transcribed (SWBD)

18.3 %

22.6 %

5 ×512 (soft target-trained)

3.4 mil.

1100 h untrans. (SWBD + FSH)

18.0%

21.4%