Frequency-centroid features for word recognition of non-native English speakers
This addresses speech recognition challenges for non-native speakers, but it is incremental as it builds on existing methods with complementary features.
The paper tackled word recognition for non-native English speakers by proposing frequency-centroid features to complement MFCCs, achieving relative performance improvements, especially in noisy conditions.
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.