LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic Challenge - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic Challenge

Abstract

This paper describes the automatic speech recognition (ASR) systems developed by LIUM in the framework of the 2016 Multi-Genre Broadcast (MGB-2) Challenge in the Arabic language. LIUM participated in the first of the two proposed tasks, namely the speech-to-text transcription of Aljazeera recordings. We present the approaches and details found in our systems, as well as our results in the evaluation campaign: the primary LIUM ASR system attained the second position. The main aspects come from the use of GMM-derived features for training a DNN, combined with the use of time-delay neural networks for acoustic models, the use of two different approaches in order to automatically phonetize Arabic words, and finally, the training data selection strategy for acoustic and language models.
No file

Dates and versions

hal-01433188 , version 1 (12-01-2017)

Identifiers

Cite

Natalia Tomashenko, Kévin Vythelingum, Anthony Rousseau, Yannick Estève. LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic Challenge. IEEE Workshop on Spoken Language Technology, Dec 2016, San Diego, CA, USA, United States. ⟨10.1109/SLT.2016.7846278⟩. ⟨hal-01433188⟩
175 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More