# Vocal Tract Length Warped Features for Spoken Keyword Spotting

arXiv: https://arxiv.org/abs/2501.03523 · HTML: https://mlsanity.com/paper/2501.03523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 7 Jan 2025.

## Builds on (most cited first, 10 of 10)

- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Keyword Transformer: A Self-Attention Model for Keyword Spotting](https://mlsanity.com/paper/2104.00769/) (2021)
- [Temporal Convolution for Real-time Keyword Spotting on Mobile Devices](https://mlsanity.com/paper/1904.03814/) (2019)
- [Broadcasted Residual Learning for Efficient Keyword Spotting](https://mlsanity.com/paper/2106.04140/) (2021)
- [Streaming keyword spotting on mobile devices](https://mlsanity.com/paper/2005.06720/) (2020)
- [A neural attention model for speech command recognition](https://mlsanity.com/paper/1808.08929/) (2018)
- [Noise-Robust Keyword Spotting through Self-supervised Pretraining](https://mlsanity.com/paper/2403.18560/) (2024)
- [DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting](https://mlsanity.com/paper/2305.12331/) (2023)
- [Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding](https://mlsanity.com/paper/2011.12536/) (2020)
- [Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units](https://mlsanity.com/paper/2407.04652/) (2024)

## Abstract (arXiv)

In this paper, we propose several methods that incorporate vocal tract length (VTL) warped features for spoken keyword spotting (KWS). The first method, VTL-independent KWS, involves training a single deep neural network (DNN) that utilizes VTL features with various warping factors. During training, a specific VTL feature is randomly selected per epoch, allowing the exploration of VTL variations. During testing, the VTL features with different warping factors of a test utterance are scored against the DNN and combined with equal weight. In the second method scores the conventional features of a test utterance (without VTL warping) against the DNN. The third method, VTL-concatenation KWS, concatenates VTL warped features to form high-dimensional features for KWS. Evaluations carried out on the English Google Command dataset demonstrate that the proposed methods improve the accuracy of KWS.