# OnDA: On-device Channel Pruning for Efficient Personalized Keyword Spotting

arXiv: https://arxiv.org/abs/2603.02247 · HTML: https://mlsanity.com/paper/2603.02247/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Hessian-Aware Pruning and Optimal Neural Implant](https://mlsanity.com/paper/2101.08940/) (2021)
- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [Efficient keyword spotting using dilated convolutions and gating](https://mlsanity.com/paper/1811.07684/) (2018)
- [Query-by-example on-device keyword spotting](https://mlsanity.com/paper/1910.05171/) (2019)
- [Few-Shot Keyword Spotting With Prototypical Networks](https://mlsanity.com/paper/2007.14463/) (2020)
- [Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge](https://mlsanity.com/paper/2301.10281/) (2023)
- [On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systems](https://mlsanity.com/paper/2403.10549/) (2024)
- [Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems](https://mlsanity.com/paper/2306.02161/) (2023)
- [Personalized Keyword Spotting through Multi-task Learning](https://mlsanity.com/paper/2206.13708/) (2022)
- [Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors](https://mlsanity.com/paper/2408.12481/) (2024)
- [Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers](https://mlsanity.com/paper/2208.02765/) (2022)

## Abstract (arXiv)

Always-on keyword spotting (KWS) demands on-device adaptation to cope with user- and environment-specific distribution shifts under tight latency and energy budgets. This paper proposes, for the first time, coupling weight adaptation (i.e., on-device training) with architectural adaptation, in the form of online structured channel pruning, for personalized on-device KWS. Starting from a state-of-the-art self-learning personalized KWS pipeline, we compare data-agnostic and data-aware pruning criteria applied on in-field pseudo-labelled user data. On the HeySnips and HeySnapdragon datasets, we achieve up to 9.63x model-size compression with respect to unpruned baselines at iso-task performance, measured as the accuracy at 0.5 false alarms per hour. When deploying our adaptation pipeline on a Jetson Orin Nano embedded GPU, we achieve up to 1.52x/1.57x and 1.64x/1.77x latency and energy-consumption improvements during online training/inference compared to weights-only adaptation.