Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition T Lohrenz, Z Li, T Fingscheidt Interspeech, 2846-2850, 2021 | 22 | 2021 |
Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition T Lohrenz, P Schwarz, Z Li, T Fingscheidt 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2021 | 12 | 2021 |
Beyond the DCASE2017 Challenge on Rare Sound Event Detection: A Proposal for a More Realistic Training and Test Framework J Baumann, T Lohrenz, A Roy, T Fingscheidt ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 12 | 2020 |
Relaxed Attention for Transformer Models T Lohrenz, B Möller, Z Li, T Fingscheidt 2023 International Joint Conference on Neural Networks (IJCNN), 1-10, 2023 | 9 | 2023 |
Turbo Fusion of Magnitude and Phase Information for DNN-based Phoneme Recognition T Lohrenz, T Fingscheidt Automatic Speech Recognition and Understanding Workshop (ASRU), 2017 IEEE …, 2017 | 9 | 2017 |
A new DCASE 2017 rare sound event detection benchmark under equal training data: CRNN with multi-width kernels J Baumann, P Meyer, T Lohrenz, A Roy, M Papendieck, T Fingscheidt ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 5 | 2021 |
A New TIMIT Benchmark for Context-Independent Phone Recognition Using Turbo Fusion T Lohrenz, W Li, T Fingscheidt 2018 IEEE Spoken Language Technology Workshop (SLT), 498-505, 2018 | 5 | 2018 |
Parameter-efficient cross-language transfer learning for a language-modular audiovisual speech recognition Z Li, T Graave, J Liu, T Lohrenz, S Kunzmann, T Fingscheidt 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023 | 4 | 2023 |
On Temporal Context Information for Hybrid BLSTM-Based Phoneme Recognition T Lohrenz, M Strake, T Fingscheidt 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019 | 4 | 2019 |
Densenet BLSTM for Acoustic Modeling in Robust ASR M Strake, P Behr, T Lohrenz, T Fingscheidt 2018 IEEE Spoken Language Technology Workshop (SLT), 6-12, 2018 | 4 | 2018 |
Transformer-Based Lip-Reading with Regularized Dropout and Relaxed Attention Z Li, T Lohrenz, M Dunkelberg, T Fingscheidt 2022 IEEE Spoken Language Technology Workshop (SLT), 723-730, 2023 | 3 | 2023 |
BLSTM-Driven Stream Fusion for Automatic Speech Recognition: Novel Methods and a Multi-Size Window Fusion Example. T Lohrenz, T Fingscheidt INTERSPEECH, 26-30, 2020 | 3 | 2020 |
An Efficient and Noise-Robust Audiovisual Encoder for Audiovisual Speech Recognition Z Li, C Liang, T Lohrenz, M Sach, B Möller, T Fingscheidt Proc. of Interspeech, 1583-1587, 2023 | 1 | 2023 |
DNN/CNN Acoustic Model Turbo Fusion for Phoneme Recognition T Lohrenz, W Li, T Fingscheidt Speech Communication; 13th ITG-Symposium, 1-5, 2018 | 1 | 2018 |
EXIT Charts for Turbo Automatic Speech Recognition: A Case Study T Lohrenz, S Receveur, T Fingscheidt Speech Communication; 12. ITG Symposium, 1-5, 2016 | 1 | 2016 |
Multi-Head Fusion Attention for Transformer-Based End-to-End Automatic Speech Recognition T Lohrenz, P Schwarz, Z Li, T Fingscheidt Speech Communication; 14th ITG Conference, 1-5, 2021 | | 2021 |
Introducing Block-Wise Processing into Turbo Viterbi ASR S Receveur, T Lohrenz, T Fingscheidt Speech Communication; 12. ITG Symposium, 1-5, 2016 | | 2016 |
REAL-TIME INTERACTIVE DEMONSTRATOR FOR AUDIOVISUAL SPEECH RECOGNITION AND LIP READING Z Li, T Lohrenz, M Dunkelberg, T Fingscheidt Anwendungen, Implikationen, Entwicklungen, 8, 0 | | |
Sprachdialogsysteme (Spoken Language Processing)(2013)(Modulnr.: ET-NT-54) T Fingscheidt, T Lohrenz Vorlesungsverzeichnis, 0 | | |