# Small-Footprint Open-Vocabulary Keyword Spotting with Quantized LSTM Networks

arXiv: https://arxiv.org/abs/2002.10851 · HTML: https://mlsanity.com/paper/2002.10851/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [Teaching keyword spotters to spot new keywords with limited examples](https://mlsanity.com/paper/2106.02443/) (2021)
- [Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors](https://mlsanity.com/paper/2408.12481/) (2024)
- [Training Integer-Only Deep Recurrent Neural Networks](https://mlsanity.com/paper/2212.11791/) (2022)
- [QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer](https://mlsanity.com/paper/2206.13231/) (2022)
- [iRNN: Integer-only Recurrent Neural Network](https://mlsanity.com/paper/2109.09828/) (2021)
- [BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line Segmentation](https://mlsanity.com/paper/2206.08977/) (2022)
- [Cortical Features for Defense Against Adversarial Audio Attacks](https://mlsanity.com/paper/2102.00313/) (2021)
- [Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning](https://mlsanity.com/paper/2409.00099/) (2024)
- [Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices](https://mlsanity.com/paper/2508.04857/) (2025)

## Abstract (arXiv)

We explore a keyword-based spoken language understanding system, in which the intent of the user can directly be derived from the detection of a sequence of keywords in the query. In this paper, we focus on an open-vocabulary keyword spotting method, allowing the user to define their own keywords without having to retrain the whole model. We describe the different design choices leading to a fast and small-footprint system, able to run on tiny devices, for any arbitrary set of user-defined keywords, without training data specific to those keywords. The model, based on a quantized long short-term memory (LSTM) neural network, trained with connectionist temporal classification (CTC), weighs less than 500KB. Our approach takes advantage of some properties of the predictions of CTC-trained networks to calibrate the confidence scores and implement a fast detection algorithm. The proposed system outperforms a standard keyword-filler model approach.