Speaker Gender Classification in Mono-Language and Cross-Language Using BLSTM Network

Abstract

Determination of speaker gender from a speech is an important subject, where can be applied to various real-world applications. This study aims to investigate the robustness of classifying gender with different speakers who speak multi-languages, specifically Arabic and English, by using the Bidirectional Long Short-Term Memory (BLSTM) network model-based classifier. For that purpose, this paper presents the mono-language and cross-language gender classification results obtained using the BLSTM model from Arabic and English language datasets were selected from the open-source Mozilla Common Voice (MCV) corpus. The proposed model has mainly based on the speech signal features, including the Gammatone Cepstral Coefficient (GTCC), Spectral Entropy, Pitch, Harmonic Ratio, Mel Frequency Cepstral Coefficient (MFCC), and Mel Spectrum. The results showed the highest accuracy of 91.76% for the Arabic-speakers model and 86.53% for the English-speakers model.