no code implementations • IWSLT 2016 • Thai-Son Nguyen, Markus Müller, Matthias Sperber, Thomas Zenkel, Kevin Kilgour, Sebastian Stüker, Alex Waibel
For the English TED task, our best combination system has a WER of 7. 8% on the development set while our other combinations gained 21. 8% and 28. 7% WERs for the English and German MSLT tasks.
no code implementations • IWSLT (EMNLP) 2018 • Matthias Sperber, Ngoc-Quan Pham, Thai-Son Nguyen, Jan Niehues, Markus Müller, Thanh-Le Ha, Sebastian Stüker, Alex Waibel
The baseline system is a cascade of an ASR system, a system to segment the ASR output and a neural machine translation system.
no code implementations • IWSLT 2017 • Thai-Son Nguyen, Markus Müller, Matthias Sperber, Thomas Zenkel, Sebastian Stüker, Alex Waibel
For the English lecture task, our best combination system has a WER of 8. 3% on the tst2015 development set while our other combinations gained 25. 7% WER for German lecture tasks.
no code implementations • EAMT 2020 • Ondřej Bojar, Dominik Macháček, Sangeet Sagar, Otakar Smrž, Jonáš Kratochvíl, Ebrahim Ansari, Dario Franceschini, Chiara Canton, Ivan Simonini, Thai-Son Nguyen, Felix Schneider, Sebastian Stücker, Alex Waibel, Barry Haddow, Rico Sennrich, Philip Williams
ELITR (European Live Translator) project aims to create a speech translation system for simultaneous subtitling of conferences and online meetings targetting up to 43 languages.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • EMNLP (IWSLT) 2019 • Ngoc-Quan Pham, Thai-Son Nguyen, Thanh-Le Ha, Juan Hussain, Felix Schneider, Jan Niehues, Sebastian Stüker, Alexander Waibel
This paper describes KIT’s submission to the IWSLT 2019 Speech Translation task on two sub-tasks corresponding to two different datasets.
no code implementations • 17 Oct 2023 • Jie Pu, Thai-Son Nguyen, Sebastian Stüker
In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems.
no code implementations • EACL 2021 • Ond{\v{r}}ej Bojar, Dominik Mach{\'a}{\v{c}}ek, Sangeet Sagar, Otakar Smr{\v{z}}, Jon{\'a}{\v{s}} Kratochv{\'\i}l, Peter Pol{\'a}k, Ebrahim Ansari, Mohammad Mahmoudi, Rishu Kumar, Dario Franceschini, Chiara Canton, Ivan Simonini, Thai-Son Nguyen, Felix Schneider, Sebastian St{\"u}ker, Alex Waibel, Barry Haddow, Rico Sennrich, Philip Williams
This paper presents an automatic speech translation system aimed at live subtitling of conference presentations.
1 code implementation • 7 Oct 2020 • Thai-Son Nguyen, Sebastian Stueker, Alex Waibel
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks.
no code implementations • WS 2020 • Dominik Macháček, Jonáš Kratochvíl, Sangeet Sagar, Matúš Žilinec, Ondřej Bojar, Thai-Son Nguyen, Felix Schneider, Philip Williams, Yuekun Yao
This paper is an ELITR system submission for the non-native speech translation task at IWSLT 2020.
no code implementations • 20 May 2020 • Ngoc-Quan Pham, Thanh-Le Ha, Tuan-Nam Nguyen, Thai-Son Nguyen, Elizabeth Salesky, Sebastian Stueker, Jan Niehues, Alexander Waibel
We also show that this model is able to better utilize synthetic data than the Transformer, and adapts better to variable sentence segmentation quality for speech translation.
no code implementations • LREC 2020 • Dario Franceschini, Chiara Canton, Ivan Simonini, Armin Schweinfurth, Adelheid Glott, Sebastian St{\"u}ker, Thai-Son Nguyen, Felix Schneider, Thanh-Le Ha, Alex Waibel, Barry Haddow, Philip Williams, Rico Sennrich, Ond{\v{r}}ej Bojar, Sangeet Sagar, Dominik Mach{\'a}{\v{c}}ek, Otakar Smr{\v{z}}
This paper presents our progress towards deploying a versatile communication platform in the task of highly multilingual live speech translation for conferences and remote meetings live subtitling.
no code implementations • 22 Mar 2020 • Thai-Son Nguyen, Ngoc-Quan Pham, Sebastian Stueker, Alex Waibel
However, when it comes to performing run-on recognition on an input stream of audio data while producing recognition results in real-time and with low word-based latency, these models face several challenges.
no code implementations • 9 Mar 2020 • Thai-Son Nguyen, Sebastian Stüker, Alex Waibel
We show that for the hybrid models, supplying additional training data from other domains with mismatched acoustic conditions does not increase the performance on specific domains.
no code implementations • 29 Oct 2019 • Thai-Son Nguyen, Sebastian Stueker, Jan Niehues, Alex Waibel
Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 30 Apr 2019 • Ngoc-Quan Pham, Thai-Son Nguyen, Jan Niehues, Markus Müller, Sebastian Stüker, Alexander Waibel
Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community.
no code implementations • 31 Mar 2019 • Thai-Son Nguyen, Sebastian Stueker, Alex Waibel
In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria.
no code implementations • 2 Feb 2019 • Thai-Son Nguyen, Sebastian Stueker, Alex Waibel
Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • COLING 2018 • Florian Dessloch, Thanh-Le Ha, Markus M{\"u}ller, Jan Niehues, Thai-Son Nguyen, Ngoc-Quan Pham, Elizabeth Salesky, Matthias Sperber, Sebastian St{\"u}ker, Thomas Zenkel, Alex Waibel, er
{\%} Combining these techniques, we are able to provide an adapted speech translation system for several European languages.