Lattice-Free Mmi Adaptation of Self-Supervised Pretrained Acoustic Models

Apoorv Vyas; Srikanth R. Madikeri; Hervé Bourlard

ICASSP 2021accepted0 citations

Lattice-Free Mmi Adaptation of Self-Supervised Pretrained Acoustic Models

Apoorv Vyas, Srikanth R. Madikeri, Hervé Bourlard

Abstract

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% on the clean and other test sets of Librispeech (100h), 10.8% on Switchboard (300h), and 4.3% on Swahili (38h) and 4.4% on Tagalog (84h) compared to the baseline trained only with supervised data.

BibTeX

@inproceedings{icassp2021_latticefreemmiad,
  title = {Lattice-Free Mmi Adaptation of Self-Supervised Pretrained Acoustic Models},
  author = {Apoorv Vyas and Srikanth R. Madikeri and Hervé Bourlard},
  booktitle = {ICASSP 2021},
  year = {2021}
}