The Speech Recognition and Machine Translation System of IOIT for IWSLT 2013
نویسندگان
چکیده
This paper describes the Automatic Speech Recognition (ASR) and Machine Translation (MT) systems developed by IOIT for the evaluation campaign of IWSLT2013. For the ASR task, using Kaldi toolkit, we developed the system based on weighted finite state transducer. The system is constructed by applying several techniques, notably, subspace Gaussian mixture models, speaker adaptation, discriminative training, system combination and SOUL, a neural network language model. The techniques used for automatic segmentation are also clarified. Besides, we compared different types of SOUL models in order to study the impact of words of previous sentences in predicting words in language modeling. For the MT task, the baseline system was built based on the open source toolkit N -code, then being augmented by using SOUL on top, i.e., in N -best rescoring phase.
منابع مشابه
The IOIT English ASR system for IWSLT 2015
This paper describes the speech recognition system of IOIT for IWSLT 2015. This year, we focus on improving acoustic and language models by applying some new training techniques based on deep neural networks compared to the last year system. There are two subsystems which are combined by using lattice minimum Bayes-Risk decoding. On the 2013 evaluations set, provided as a test set, we are able ...
متن کاملThe Speech Recognition Systems of IOIT for IWSLT
This paper describes the speech recognition systems of IOIT for IWSLT 2014 TED ASR track. This year, we focus on improving acoustic model for the systems using two main approaches of deep neural network which are hybrid and bottleneck feature systems. These two subsystems are combined using lattice Minimum Bayes-Risk decoding. On the 2013 evaluations set, which serves as a progress test set, we...
متن کاملNLPR translation system for IWSLT 2006 evaluation campaign
In this paper we describe a hybrid approach to Chinese-toEnglish spoken language translation system used for the IWSLT 2006 evaluation campaign. In this system, the phrasebased statistical machine translation (SMT) engine is combined with the template-based machine translation (TBMT) engine and a simple way is proposed to select the best translation from the results generated by the two transla...
متن کاملThe USFD SLT system for IWSLT
The University of Sheffield (USFD) participated in the International Workshop for Spoken Language Translation (IWSLT) in 2014. In this paper, we will introduce the USFD SLT system for IWSLT. Automatic speech recognition (ASR) is achieved by two multi-pass deep neural network systems with adaptation and rescoring techniques. Machine translation (MT) is achieved by a phrase-based system. The USFD...
متن کاملThe TÜbİTAK-UEKAE statistical machine translation system for IWSLT 2007
We describe the TÜBITAK-UEKAE system that participated in the Arabic-to-English and Japanese-toEnglish translation tasks of the IWSLT 2007 evaluation campaign. Our system is built on the open-source phrasebased statistical machine translation software Moses. Among available corpora and linguistic resources, only the supplied training data and an Arabic morphological analyzer are used in the sys...
متن کامل