Vocal Tract Length Warped Features for Spoken Keyword Spotting

TL;DR

This paper introduces VTL-warped features and novel methods for spoken keyword spotting, enhancing accuracy by incorporating vocal tract length variations through training and feature concatenation techniques.

Contribution

It presents new VTL-based feature methods and training strategies that improve keyword spotting performance over conventional approaches.

Findings

VTL-independent KWS with random VTL feature selection improves accuracy.

Concatenating VTL warped features enhances keyword spotting performance.

Proposed methods outperform traditional features on Google Command dataset.

Abstract

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.