-
The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment2020 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis
Wei Guo Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schlüter, Hermann Ney
47citations -
Conformer-Based Hybrid ASR System For Switchboard Dataset2022 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access
Mohammad Zeineldeen, Jingjing Xu, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney
22citations -
Improved Robustness to Disfluencies in Rnn-Transducer Based Speech Recognition2021 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access
Valentin Mendelev, Tina Raissi, Guglielmo Camporese, Manuel Giollo
19citations -
Enhancing and Adversarial: Improve ASR with Speaker Labels2023 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access
Wei Guo Zhou, Haotian Wu, Jingjing Xu, Mohammad Zeineldeen, Christoph Lüscher, Ralf Schlüter, +1 more
6citations -
Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition2020 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis
Parnia Bahar, Nikita Makarov, Albert Zeyer, Ralf Schlüter, Hermann Ney
5citations -
How Much Self-Attention Do We Needƒ Trading Attention for Feed-Forward Layers2020 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis cited by 2 patents
Kazuki Irie, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney
4citations -
Efficient Sequence Training of Attention Models Using Approximative Recombination2022 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis
Nils-Philipp Wynands, Wilfried Michel, Jan Rosendahl, Ralf Schlüter, Hermann Ney
3citations -
Robust Knowledge Distillation from RNN-T Models with Noisy Training Labels Using Full-Sum Loss2023 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis
Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar, Bhuvana Ramabhadran
2citations
25 results