Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models

12/28/2020
by   Apoorv Vyas, et al.
0

In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretrained acoustic model. We pretrain a Transformer model on thousand hours of untranscribed Librispeech data followed by supervised adaptation with LFMMI on three different datasets. Our results show that fine-tuning with LFMMI, we consistently obtain relative WER improvements of 10 and 35.3 Switchboard (300h), and 4.3 compared to the baseline trained only with supervised data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset