Table 1 WER (%) for 6 ×2048 network with soft targets from cross-entropy-trained teacher with fMLLR inputs
Input features | Targets | Data | Hub5’00-SWB | RT03S-FSH |
|---|---|---|---|---|
FMLLR | Hard alignment | 110 h transcribed | 16.9 % | 20.1 % |
FBANK | Hard alignment | 110 h transcribed | 19.9 % | 25.1 % |
FBANK | FMLLR-XEnt outputs | 110 h untranscribed | 19.5 % | 24.2 % |
FBANK | FMLLR-XEnt outputs | 300 h untranscribed | 18.4 % | 22.7 % |