Skip to main content
. Author manuscript; available in PMC: 2021 Sep 1.
Published in final edited form as: Comput Speech Lang. 2020 Feb 18;63:101077. doi: 10.1016/j.csl.2020.101077

Table 7:

Adaptation at extreme low data scenarios

Adaptation Data Model (training) WER
35 minutes 1 layer 36.47%
35 minutes 1 layer (dis-joint) 34.13%
35 minutes 2 layers (simultaneous) 35.73%
35 minutes 2 layers (dis-joint) 35.04%
45 minutes 1 layer 35.23%
45 minutes 1 layer (dis-joint) 33.62%
45 minutes 2 layers (simultaneous) 35.13%
45 minutes 2 layers (dis-joint) 34.33%
2 hours 1 layer 33.25%
2 hours 1 layer (dis-joint) 33.62%
2 hours 2 layers (simultaneous) 32.35%
2 hours 2 layers (dis-joint) 32.94%