Development of Hausa dataset a baseline for speech recognition

Abstract

The Hausa language read-speech dataset was created by recording native Hausa speakers. The recording took place at Nile university of Nigeria audio studio and radio broadcasting studio. The recorded dataset was segmented into unigram and bigram. The Hausa speech dataset contain 47hr of recorded audio speech. The dataset can be used for automatic speech recognition, speech synthesis, Text-to-Speech and speech-to-text application