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

2020/12/28 by Vyas, Apoorv, Madikeri, Srikanth, Bourlard, Hervé · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2012.14252

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.

Cited by

• Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead

Related

• Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0\n acoustic model
• A Treatise On FST Lattice Based MMI Training
• Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models
• Lattice-based lightly-supervised acoustic model training
• Unsupervised Model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition