# LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions

arXiv: https://arxiv.org/abs/2307.06610 · HTML: https://mlsanity.com/paper/2307.06610/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 13 Jul 2023.

## Built on by (most cited first, 1 of 1)

- [Low-Resource Audio Codec (LRAC): 2025 Challenge Description](https://mlsanity.com/paper/2510.23312/) (2025)

## Abstract (arXiv)

Classical speech coding uses low-complexity postfilters with zero lookahead to enhance the quality of coded speech, but their effectiveness is limited by their simplicity. Deep Neural Networks (DNNs) can be much more effective, but require high complexity and model size, or added delay. We propose a DNN model that generates classical filter kernels on a per-frame basis with a model of just 300~K parameters and 100~MFLOPS complexity, which is a practical complexity for desktop or mobile device CPUs. The lack of added delay allows it to be integrated into the Opus codec, and we demonstrate that it enables effective wideband encoding for bitrates down to 6 kb/s.