Neyshekar: An Open Persian Read-Speech Corpus for Automatic Speech Recognition
Neyshekar is presented as an open Persian read-speech corpus designed for coverage of both formal and informal language, named entities, and longer utterances, and utility is assessed through two ASR architectures, three optimisation seeds, WER and CER, and independent evaluation on the public PSRB sample.
Ahmad Amirivojdan, Farzad Nadiri, Abolfazl Alizadeh et al.
· 0 citations