| Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data G Keren, B Schuller International Joint Conference on Neural Networks (IJCNN), 2016, 3412-3419, 2016 | 183 | 2016 |
| Contextual RNN-T for open domain ASR M Jain, G Keren, J Mahadeokar, G Zweig, F Metze, Y Saraf INTERSPEECH 2020, 2020 | 99 | 2020 |
| Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion D Le, M Jain, G Keren, S Kim, Y Shi, J Mahadeokar, J Chan, ... INTERSPEECH 2021, 2021 | 84 | 2021 |
| Deep shallow fusion for RNN-T personalization D Le, G Keren, J Chan, J Mahadeokar, C Fuegen, ML Seltzer 2021 IEEE Spoken Language Technology Workshop (SLT), 251-257, 2021 | 81 | 2021 |
| Alignment restricted streaming recurrent neural network transducer J Mahadeokar, Y Shangguan, D Le, G Keren, H Su, T Le, CF Yeh, ... 2021 IEEE Spoken Language Technology Workshop (SLT), 52-59, 2021 | 70 | 2021 |
| Towards Robust Speech Emotion Recognition Using Deep Residual Networks for Speech Enhancement A Triantafyllopoulos, G Keren, J Wagner, I Steiner, B Schuller INTERSPEECH, 1691-1695, 2019 | 66 | 2019 |
| End-to-End Learning for Dimensional Emotion Recognition from Physiological Signals G Keren, T Kirschstein, E Marchi, F Ringeval, B Schuller IEEE International Conference on Multimedia and Expo (ICME), 985-990, 2017 | 61 | 2017 |
| Calibrated Prediction Intervals for Neural Network Regressors G Keren, N Cummins, B Schuller IEEE Access 6, 54033 - 54041, 2018 | 39 | 2018 |
| A time-domain convolutional recurrent network for packet loss concealment J Lin, Y Wang, K Kalgaonkar, G Keren, D Zhang, C Fuegen ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 36 | 2021 |
| CAST a Database: Rapid Targeted Large-Scale Big Data Acquisition via Small-World Modelling of Social Media Platforms S Amiriparian, S Pugachevskiy, N Cummins, S Hantke, J Pohjalainen, ... Affective Computing and Intelligent Interaction, 2017 | 34 | 2017 |
| Convolutional neural networks with data augmentation for classifying speakers' native language G Keren, J Deng, J Pohjalainen, B Schuller | 30 | 2016 |
| Scaling asr improves zero and few shot learning A Xiao, W Zheng, G Keren, D Le, F Zhang, C Fuegen, O Kalinli, Y Saraf, ... arXiv preprint arXiv:2111.05948, 2021 | 22 | 2021 |
| Fast Single-Class Classification and the Principle of Logit Separation G Keren, S Sabato, B Schuller International Conference on Data Mining (ICDM), 2018 | 20 | 2018 |
| Scaling Speech Enhancement in Unseen Environments with Noise Embeddings G Keren, J Han, B Schuller the Fifth CHiME Challenge Workshop, 2018 | 20 | 2018 |
| Deep learning for multisensorial and multimodal interaction G Keren, AED Mousa, O Pietquin, S Zafeiriou, B Schuller The Handbook of Multimodal-Multisensor Interfaces: Signal Processing …, 2018 | 18 | 2018 |
| N-HANS: A neural network-based toolkit for in-the-wild audio enhancement S Liu, G Keren, E Parada-Cabaleiro, B Schuller Multimedia Tools and Applications 80 (18), 28365-28389, 2021 | 16 | 2021 |
| Emotion recognition in speech with latent discriminative representations learning J Han, Z Zhang, G Keren, B Schuller Acta Acustica united with Acustica 104 (5), 737-740, 2018 | 16 | 2018 |
| A Two-Stage Approach to Speech Bandwidth Extension. J Lin, Y Wang, K Kalgaonkar, G Keren, D Zhang, C Fuegen Interspeech, 1689-1693, 2021 | 13 | 2021 |
| Tunable Sensitivity to Large Errors in Neural Network Training G Keren, S Sabato, BW Schuller AAAI, 2087-2093, 2017 | 10 | 2017 |
| Weakly supervised one-shot detection with attention Siamese networks G Keren, M Schmitt, T Kehrenberg, B Schuller arXiv preprint arXiv:1801.03329, 1-12, 2018 | 9 | 2018 |
