[PDF][PDF] Improvements in RWTH LVCSR evaluation systems for Polish, Portuguese, English, urdu, and Arabic.

MAB Shaik, Z Tüske, MA Tahir, M Nußbaum-Thom… - …, 2015 - isca-archive.org
Abstract In this work, Portuguese, Polish, English, Urdu, and Arabic automatic speech
recognition evaluation systems developed by the RWTH Aachen University are presented …

The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task

W Michel, Z Tüske, MAB Shaik… - Proceedings of the …, 2016 - aclanthology.org
In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems
developed for the IWSLT-2016 evaluation campaign are described. This evaluation …

[PDF][PDF] Investigation on language modelling approaches for open vocabulary speech recognition

B Shaik, M Ali - 2016 - publications.rwth-aachen.de
By definition, words that are not present in a recognition vocabulary are called out-of-
vocabulary (OOV) words. Recognition of unseen or new words is an important feature that is …

[PDF][PDF] Discriminative training of linear transformations and mixture density splitting for speech recognition

MA Tahir - 2015 - d-nb.info
Discriminative training has been established as an effective technique for training the
acoustic model of an automatic speech recognition system. It reduces the word error rate as …

[PDF][PDF] Investigations on neural networks, discriminative training criteria and error bounds

M Nußbaum-Thom - 2020 - publications.rwth-aachen.de
The task of an automatic speech recognition system is to convert speech signals into written
text by choosing the recognition result according to a statistical decision rule. The …

[PDF][PDF] Discriminative feature modeling for statistical speech recognition

Z Tüske - 2020 - scholar.archive.org
Conventional speech recognition systems consist of feature extraction, acoustic and
language modeling blocks, and search block. In a recent trend the traditional modeling …