The USTC-NEL Speech Translation system at IWSLT 2018

Autor:	Liu, Dan, Liu, Junhua, Guo, Wu, Xiong, Shifu, Ma, Zhiqiang, Song, Rui, Wu, Chongliang, Liu, Quan
Rok vydání:	2018
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine translation. We train a group of hybrid-HMM models for our speech recognition, and for machine translation we train transformer based neural machine translation models with speech recognition output style text as input. Experiments conducted on the IWSLT 2018 task indicate that, compared to baseline system from KIT, our system achieved 14.9 BLEU improvement. Comment: 5 pages, 8 tabels
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1812.02455 Zobrazit plný text záznamu View this record from Arxiv