# Text Anchor Based Metric Learning for Small-footprint Keyword Spotting

arXiv: https://arxiv.org/abs/2108.05516 · HTML: https://mlsanity.com/paper/2108.05516/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 12 Aug 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Temporal Convolution for Real-time Keyword Spotting on Mobile Devices](https://mlsanity.com/paper/1904.03814/) (2019)
- [Attention-based End-to-End Models for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1803.10916/) (2018)
- [Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution](https://mlsanity.com/paper/2010.09960/) (2020)
- [Neural Architecture Search For Keyword Spotting](https://mlsanity.com/paper/2009.00165/) (2020)
- [Metric Learning for Keyword Spotting](https://mlsanity.com/paper/2005.08776/) (2020)
- [Data Augmentation for Robust Keyword Spotting under Playback Interference](https://mlsanity.com/paper/1808.00563/) (2018)
- [Sequence-to-sequence Models for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1811.00348/) (2018)

## Built on by (most cited first, 3 of 3)

- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [Boosting Tail Neural Network for Realtime Custom Keyword Spotting](https://mlsanity.com/paper/2205.12933/) (2022)
- [Keyword Mamba: Spoken Keyword Spotting with State Space Models](https://mlsanity.com/paper/2508.07363/) (2025)

## Abstract (arXiv)

Keyword Spotting (KWS) remains challenging to achieve the trade-off between small footprint and high accuracy. Recently proposed metric learning approaches improved the generalizability of models for the KWS task, and 1D-CNN based KWS models have achieved the state-of-the-arts (SOTA) in terms of model size. However, for metric learning, due to data limitations, the speech anchor is highly susceptible to the acoustic environment and speakers. Also, we note that the 1D-CNN models have limited capability to capture long-term temporal acoustic features. To address the above problems, we propose to utilize text anchors to improve the stability of anchors. Furthermore, a new type of model (LG-Net) is exquisitely designed to promote long-short term acoustic feature modeling based on 1D-CNN and self-attention. Experiments are conducted on Google Speech Commands Dataset version 1 (GSCDv1) and 2 (GSCDv2). The results demonstrate that the proposed text anchor based metric learning method shows consistent improvements over speech anchor on representative CNN-based models. Moreover, our LG-Net model achieves SOTA accuracy of 97.67% and 96.79% on two datasets, respectively. It is encouraged to see that our lighter LG-Net with only 74k parameters obtains 96.82% KWS accuracy on the GSCDv1 and 95.77% KWS accuracy on the GSCDv2.