# Stacked 1D convolutional networks for end-to-end small footprint voice trigger detection

arXiv: https://arxiv.org/abs/2008.03405 · HTML: https://mlsanity.com/paper/2008.03405/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows](https://mlsanity.com/paper/2201.07677/) (2022)
- [LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting](https://mlsanity.com/paper/2211.04635/) (2022)
- [MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting](https://mlsanity.com/paper/2406.07310/) (2024)
- [HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words](https://mlsanity.com/paper/2210.15425/) (2022)
- [Multi-task Learning with Cross Attention for Keyword Spotting](https://mlsanity.com/paper/2107.07634/) (2021)
- [Streaming Anchor Loss: Augmenting Supervision with Temporal Significance](https://mlsanity.com/paper/2310.05886/) (2023)
- [RepCNN: Micro-sized, Mighty Models for Wakeword Detection](https://mlsanity.com/paper/2406.02652/) (2024)

## Abstract (arXiv)

We propose a stacked 1D convolutional neural network (S1DCNN) for end-to-end small footprint voice trigger detection in a streaming scenario. Voice trigger detection is an important speech application, with which users can activate their devices by simply saying a keyword or phrase. Due to privacy and latency reasons, a voice trigger detection system should run on an always-on processor on device. Therefore, having small memory and compute cost is crucial for a voice trigger detection system. Recently, singular value decomposition filters (SVDFs) has been used for end-to-end voice trigger detection. The SVDFs approximate a fully-connected layer with a low rank approximation, which reduces the number of model parameters. In this work, we propose S1DCNN as an alternative approach for end-to-end small-footprint voice trigger detection. An S1DCNN layer consists of a 1D convolution layer followed by a depth-wise 1D convolution layer. We show that the SVDF can be expressed as a special case of the S1DCNN layer. Experimental results show that the S1DCNN achieve 19.0% relative false reject ratio (FRR) reduction with a similar model size and a similar time delay compared to the SVDF. By using longer time delays, the S1DCNN further improve the FRR up to 12.2% relative.