VFNet: A Convolutional Architecture for Accent Classification

TL;DR

This paper introduces VFNet, a CNN-based architecture with variable filter sizes for improved accent classification, enhancing the accuracy of identifying spoken accents in human-machine interactions.

Contribution

VFNet employs a novel variable filter size technique along the frequency band, achieving superior performance over previous accent classification methods.

Findings

Outperforms previous benchmarks in accent classification accuracy

Utilizes variable filter sizes to capture hierarchical audio features

Demonstrates effectiveness on speech datasets

Abstract

Understanding accent is an issue which can derail any human-machine interaction. Accent classification makes this task easier by identifying the accent being spoken by a person so that the correct words being spoken can be identified by further processing, since same noises can mean entirely different words in different accents of the same language. In this paper, we present VFNet (Variable Filter Net), a convolutional neural network (CNN) based architecture which captures a hierarchy of features to beat the previous benchmarks of accent classification, through a novel and elegant technique of applying variable filter sizes along the frequency band of the audio utterances.