| Character-word LSTM language models L Verwimp, J Pelemans, P Wambacq arXiv preprint arXiv:1704.02813, 2017 | 68 | 2017 |
| Sparse non-negative matrix language modeling for skip-grams. N Shazeer, J Pelemans, C Chelba Interspeech, 1428-1432, 2015 | 32 | 2015 |
| Automatic assessment of children's reading with the FLaVoR decoding using a phone confusion model E Yilmaz, J Pelemans, H Van Hamme International Speech and Communication Association, 2014 | 17 | 2014 |
| Skip-gram language modeling using sparse non-negative matrix probability estimation N Shazeer, J Pelemans, C Chelba arXiv preprint arXiv:1412.1454, 2014 | 15 | 2014 |
| Improving the translation environment for professional translators V Vandeghinste, T Vanallemeersch, L Augustinus, B Bulté, F Van Eynde, ... Informatics 6 (2), 24, 2019 | 12 | 2019 |
| A comparison of different punctuation prediction approaches in a translation context V Vandeghinste, L Verwimp, J Pelemans, P Wambacq European Association for Machine Translation, 2018 | 11 | 2018 |
| Analyzing the Contribution of Top-Down Lexical and Bottom-Up Acoustic Cues in the Detection of Sentence Prominence. S Kakouros, J Pelemans, L Verwimp, P Wambacq, O Räsänen Interspeech, 1074-1078, 2016 | 11 | 2016 |
| Sparse non-negative matrix language modeling J Pelemans, N Shazeer, C Chelba Transactions of the Association for Computational Linguistics 4, 329-342, 2016 | 7 | 2016 |
| SCATE-Smart Computer Aided Translation Environment. V Vandeghinste, T Vanallemeersch, L Augustinus, J Pelemans, ... Baltic Journal of Modern Computing 4 (2), 2016 | 7 | 2016 |
| Pruning sparse non-negative matrix n-gram language models. J Pelemans, N Shazeer, C Chelba Interspeech, 1433-1437, 2015 | 7 | 2015 |
| Van hamme, H., and Wambacq, P.(2019) L Verwimp, J Pelemans Tf-lm: Tensorflow-based language modeling toolkit. In http://www. lrec-conf …, 0 | 7 | |
| Coping with language data sparsity: Semantic head mapping of compound words J Pelemans, K Demuynck, P Wambacq 2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014 | 6 | 2014 |
| Efficient language model adaptation for automatic speech recognition of spoken translations J Pelemans, T Vanallemeersch, K Demuynck, P Wambacq 16th Annual Conference of the International Speech Communication Association …, 2015 | 5 | 2015 |
| A layered approach for dutch large vocabulary continuous speech recognition J Pelemans, K Demuynck, P Wambacq 2012 IEEE international conference on acoustics, speech and signal …, 2012 | 5 | 2012 |
| User-initiated repetition-based recovery in multi-utterance dialogue systems HL Nguyen, V Renkens, J Pelemans, SP Potharaju, AK Nalamalapu, ... arXiv preprint arXiv:2108.01208, 2021 | 4 | 2021 |
| Language model adaptation for ASR of spoken translations using phrase-based translation models and named entity models J Pelemans, T Vanallemeersch, K Demuynck, L Verwimp, P Wambacq 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 4 | 2016 |
| STON efficient subtitling in Dutch using state-of-the-art tools L Verwimp, B Desplanques, K Demuynck, J Pelemans, M Lycke, ... 17th Annual Conference of the International-Speech-Communication-Association …, 2016 | 4 | 2016 |
| Integrating meta-information into recurrent neural network language models Y Shi, M Larson, J Pelemans, CM Jonker, P Wambacq, P Wiggers, ... Speech Communication 73, 64-80, 2015 | 4 | 2015 |
| Information-weighted neural cache language models for asr L Verwimp, J Pelemans, P Wambacq 2018 IEEE Spoken Language Technology Workshop (SLT), 756-762, 2018 | 3 | 2018 |
| Domain adaptation for LSTM language models W Boes, R Van Rompaey, J Pelemans, L Verwimp, P Wambacq Book of abstracts CLIN27, 57, 2017 | 3 | 2017 |
Lyan VerwimpKU LeuvenVerified email at esat.kuleuven.be
