Generating synthetic audio data for attention-based speech recognition systems N Rossenbach, A Zeyer, R Schlüter, H Ney ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 92 | 2020 |
The RWTH Aachen University filtering system for the WMT 2018 parallel corpus filtering task N Rossenbach, J Rosendahl, Y Kim, M Graça, A Gokrani, H Ney Proceedings of the Third Conference on Machine Translation: Shared Task …, 2018 | 27 | 2018 |
The rwth aachen university english-german and german-english machine translation system for wmt 2017 JT Peter, A Guta, T Alkhouli, P Bahar, J Rosendahl, N Rossenbach, ... Proceedings of the Second Conference on Machine Translation, 358-365, 2017 | 11 | 2017 |
The RWTH Aachen machine translation systems for IWSLT 2017 P Bahar, J Rosendahl, N Rossenbach, H Ney Proceedings of the 14th International Conference on Spoken Language …, 2017 | 10 | 2017 |
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures N Rossenbach, M Zeineldeen, B Hilmes, R Schlüter, H Ney 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2021 | 9 | 2021 |
The RWTH Aachen Machine Translation System for IWSLT 2016 JT Peter, A Guta, N Rossenbach, MM Graça, H Ney International Workshop on Spoken Language Translation 13, 2016 | 9 | 2016 |
Automatic video dubbing at AppTek MA Di Gangi, N Rossenbach, A Pérez, P Bahar, E Beck, P Wilken, ... Proceedings of the 23rd Annual Conference of the European Association for …, 2022 | 5 | 2022 |
Learning bilingual sentence embeddings via autoencoding and computing similarities with a multilayer perceptron Y Kim, H Rosendahl, N Rossenbach, J Rosendahl, S Khadivi, H Ney arXiv preprint arXiv:1906.01942, 2019 | 4 | 2019 |
On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition N Rossenbach, B Hilmes, R Schlüter 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023 | 2 | 2023 |
Take the hint: Improving Arabic diacritization with partially-diacritized text P Bahar, M Di Gangi, N Rossenbach, M Zeineldeen arXiv preprint arXiv:2306.03557, 2023 | 2 | 2023 |
On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition N Rossenbach, R Schlüter, S Sakti arXiv preprint arXiv:2407.21476, 2024 | | 2024 |
On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures N Rossenbach, B Hilmes, R Schlüter arXiv preprint arXiv:2407.17997, 2024 | | 2024 |