# Latency Control for Keyword Spotting

arXiv: https://arxiv.org/abs/2206.07261 · HTML: https://mlsanity.com/paper/2206.07261/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 6 of 6)

- [Accurate Detection of Wake Word Start and End Using a CNN](https://mlsanity.com/paper/2008.03790/) (2020)
- [Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1705.02411/) (2017)
- [Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization](https://mlsanity.com/paper/2108.01704/) (2021)
- [Progressive Voice Trigger Detection: Accuracy vs Latency](https://mlsanity.com/paper/2010.15446/) (2020)
- [Tiny-CRNN: Streaming Wakeword Detection In A Low Footprint Setting](https://mlsanity.com/paper/2109.14725/) (2021)
- [Small Footprint Convolutional Recurrent Networks for Streaming Wakeword Detection](https://mlsanity.com/paper/2011.12941/) (2020)

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

- [Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting](https://mlsanity.com/paper/2607.20086/) (2026)

## Abstract (arXiv)

Conversational agents commonly utilize keyword spotting (KWS) to initiate voice interaction with the user. For user experience and privacy considerations, existing approaches to KWS largely focus on accuracy, which can often come at the expense of introduced latency. To address this tradeoff, we propose a novel approach to control KWS model latency and which generalizes to any loss function without explicit knowledge of the keyword endpoint. Through a single, tunable hyperparameter, our approach enables one to balance detection latency and accuracy for the targeted application. Empirically, we show that our approach gives superior performance under latency constraints when compared to existing methods. Namely, we make a substantial 25% relative false accepts improvement for a fixed latency target when compared to the baseline state-of-the-art. We also show that when our approach is used in conjunction with a max-pooling loss, we are able to improve relative false accepts by 25 % at a fixed latency when compared to cross entropy loss.