# Frequency-centroid features for word recognition of non-native English speakers

arXiv: https://arxiv.org/abs/2206.07176 · HTML: https://mlsanity.com/paper/2206.07176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1703.05390/) (2017)
- [CloudSegNet: A Deep Network for Nychthemeron Cloud Image Segmentation](https://mlsanity.com/paper/1904.07979/) (2019)
- [DMCNet: Diversified Model Combination Network for Understanding Engagement from Video Screengrabs](https://mlsanity.com/paper/2204.06454/) (2022)
- [Keyword Spotting for Hearing Assistive Devices Robust to External Speakers](https://mlsanity.com/paper/1906.09417/) (2019)
- [Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verification](https://mlsanity.com/paper/1909.11886/) (2019)
- [ADNet: A Deep Network for Detecting Adverts](https://mlsanity.com/paper/1811.04115/) (2018)
- [TEST: A Terminology Extraction System for Technology Related Terms](https://mlsanity.com/paper/1812.09541/) (2018)
- [Analysis of French Phonetic Idiosyncrasies for Accent Recognition](https://mlsanity.com/paper/2110.09179/) (2021)

## Abstract (arXiv)

The objective of this work is to investigate complementary features which can aid the quintessential Mel frequency cepstral coefficients (MFCCs) in the task of closed, limited set word recognition for non-native English speakers of different mother-tongues. Unlike the MFCCs, which are derived from the spectral energy of the speech signal, the proposed frequency-centroids (FCs) encapsulate the spectral centres of the different bands of the speech spectrum, with the bands defined by the Mel filterbank. These features, in combination with the MFCCs, are observed to provide relative performance improvement in English word recognition, particularly under varied noisy conditions. A two-stage Convolution Neural Network (CNN) is used to model the features of the English words uttered with Arabic, French and Spanish accents.