# Predicting detection filters for small footprint open-vocabulary keyword spotting

arXiv: https://arxiv.org/abs/1912.07575 · HTML: https://mlsanity.com/paper/1912.07575/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2019.

## Built on by (most cited first, 10 of 10)

- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [Few-Shot Keyword Spotting in Any Language](https://mlsanity.com/paper/2104.01454/) (2021)
- [Teaching keyword spotters to spot new keywords with limited examples](https://mlsanity.com/paper/2106.02443/) (2021)
- [Text-Aware Adapter for Few-Shot Keyword Spotting](https://mlsanity.com/paper/2412.18142/) (2024)
- [Multi-task Learning with Cross Attention for Keyword Spotting](https://mlsanity.com/paper/2107.07634/) (2021)
- [Automatic Speech Recognition And Limited Vocabulary: A Survey](https://mlsanity.com/paper/2108.10254/) (2021)
- [A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning](https://mlsanity.com/paper/2202.08509/) (2022)
- [End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations](https://mlsanity.com/paper/2308.08027/) (2023)
- [Written Term Detection Improves Spoken Term Detection](https://mlsanity.com/paper/2407.04601/) (2024)
- [Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices](https://mlsanity.com/paper/2508.04857/) (2025)

## Abstract (arXiv)

In this paper, we propose a fully-neural approach to open-vocabulary keyword spotting, that allows the users to include a customizable voice interface to their device and that does not require task-specific data. We present a keyword detection neural network weighing less than 250KB, in which the topmost layer performing keyword detection is predicted by an auxiliary network, that may be run offline to generate a detector for any keyword. We show that the proposed model outperforms acoustic keyword spotting baselines by a large margin on two tasks of detecting keywords in utterances and three tasks of detecting isolated speech commands. We also propose a method to fine-tune the model when specific training data is available for some keywords, which yields a performance similar to a standard speech command neural network while keeping the ability of the model to be applied to new keywords.