DNN-Based Speech Recognition for Globalphone Languages
Martha Yifiru Tachbelie, Ayimunishagu Abulimiti, Solomon Teferra Abate, Tanja Schultz
Abstract
This paper describes new reference benchmark results based on hybrid Hidden Markov Model and Deep Neural Networks (HMM-DNN) for the GlobalPhone (GP) multilingual text and speech database. GP is a multilingual database of high-quality read speech with corresponding transcriptions and pronunciation dictionaries in more than 20 languages. Moreover, we provide new results for five additional languages, namely, Amharic, Oromo, Tigrigna, Wolaytta, and Uyghur. Across the 22 languages considered, the hybrid HMM-DNN models outperform the HMM-GMM based models regardless of the size of the training speech used. Overall, we achieved relative improvements that range from 7.14% to 59.43%.
BibTeX
@inproceedings{icassp2020_dnnbasedspeechre,
title = {DNN-Based Speech Recognition for Globalphone Languages},
author = {Martha Yifiru Tachbelie and Ayimunishagu Abulimiti and Solomon Teferra Abate and Tanja Schultz},
booktitle = {ICASSP 2020},
year = {2020}
}