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

arXiv: https://arxiv.org/abs/2012.14252 · HTML: https://mlsanity.com/paper/2012.14252/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications](https://mlsanity.com/paper/2203.16822/) (2022)
- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model](https://mlsanity.com/paper/2104.02558/) (2021)
- [A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers](https://mlsanity.com/paper/2304.07842/) (2023)
- [Injecting Text and Cross-lingual Supervision in Few-shot Learning from Self-Supervised Models](https://mlsanity.com/paper/2110.04863/) (2021)

## Abstract (arXiv)

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.