Analyzing hidden representations in end-to-end automatic speech recognition systems, Advances in Neural Information Processing Systems, pp.2438-2448, 2017. ,
Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks, Proceedings of the Eighth International Joint Conference on Natural Language Processing, pp.1-10, 2017. ,
Keras. https, 2015. ,
Very deep convolutional neural networks for raw waveforms, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.421-425, 2017. ,
DOI : 10.1109/ICASSP.2017.7952190
URL : http://arxiv.org/pdf/1610.00087
Asr performance prediction on unseen broadcast programs using convolutional neural networks, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01709779
The ester phase ii evaluation campaign for the rich transcription of french broadcast news, Interspeech, pp.1149-1152, 2005. ,
The etape corpus for the evaluation of speech-based tv content processing in the french language, LREC-Eighth international conference on Language Resources and Evaluation, p.page na, 2012. ,
URL : https://hal.archives-ouvertes.fr/hal-00712591
A presentation of the REPERE challenge, 2012 10th International Workshop on Content-Based Multimedia Indexing (CBMI), pp.1-6, 2012. ,
DOI : 10.1109/CBMI.2012.6269851
Convolutional neural networks for sentence classification. arXiv preprint, 2014. ,
DOI : 10.3115/v1/d14-1181
URL : https://doi.org/10.3115/v1/d14-1181
Adam: A method for stochastic optimization. CoRR, abs/1412, 2014. ,
Visualizing data using t-sne, Journal of machine learning research, vol.9, pp.2579-2605, 2008. ,
Understanding how deep belief networks perform acoustic modelling, Acoustics , Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, pp.4273-4276, 2012. ,
The kaldi speech recognition toolkit, IEEE 2011 workshop on automatic speech recognition and understanding, EPFL- CONF-192584, 2011. ,
Does String-Based Neural MT Learn Source Syntax?, Proceedings of the 2016 Conference on Empirical Methods in Natural
Language Processing, pp.1526-1534, 2016. ,
DOI : 10.18653/v1/D16-1159
URL : https://doi.org/10.18653/v1/d16-1159
What does the speaker embedding encode? In Interspeech, pp.1497-1501, 2017. ,
Investigating gated recurrent neural networks for speech synthesis . CoRR, abs/1601, 2016. ,
DOI : 10.1109/icassp.2016.7472657