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

06/14/2022
by   Pierre Berjon, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/16/2018

The Relevance of Text and Speech Features in Automatic Non-native English Accent Identification

This paper describes our experiments with automatically identifying nati...
research
02/23/2017

Pronunciation recognition of English phonemes /@/, /æ/, /A:/ and /2/ using Formants and Mel Frequency Cepstral Coefficients

The Vocal Joystick Vowel Corpus, by Washington University, was used to s...
research
06/07/2021

Weakly-supervised word-level pronunciation error detection in non-native English speech

We propose a weakly-supervised model for word-level mispronunciation det...
research
04/15/2022

Decoding Neural Correlation of Language-Specific Imagined Speech using EEG Signals

Speech impairments due to cerebral lesions and degenerative disorders ca...
research
08/29/2018

Characterizing the Influence of Features on Reading Difficulty Estimation for Non-native Readers

In recent years, the number of people studying English as a second langu...
research
06/09/2019

In Situ Cane Toad Recognition

Cane toads are invasive, toxic to native predators, compete with native ...
research
02/25/2016

Adaptive Frequency Cepstral Coefficients for Word Mispronunciation Detection

Systems based on automatic speech recognition (ASR) technology can provi...

Please sign up or login with your details

Forgot password? Click here to reset