Sorry, you need to enable JavaScript to visit this website.

DNN-BASED SPEECH RECOGNITION FOR GLOBALPHONE LANGUAGES

Citation Author(s):
Martha Yifiru Tachbelie, Ayimunishagu Abulimiti, Solomon Teferra Abate, Tanja Schultz
Submitted by:
Martha Tachbelie
Last updated:
20 May 2020 - 9:12am
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters:
Martha Yifiru Tachbelie
Paper Code:
5018
 

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%.

up
0 users have voted: