Speaker diarization using bottom-up clustering based on a parameter-derived distance between adapted GMMs, Proceedings of the 8th International Conference on Spoken Language Processing, pp.333-444, 2004. ,
Multimodal person discovery in broadcast TV at MediaEval 2016, Working notes of the MediaEval 2016 Workshop, 2016. ,
SSIG and IRISA at Multimodal Person Discovery, Working notes of the MediaEval 2015 Workshop, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01196171
EUMSSI team at the MediaEval Person Discovery Challenge, Working notes of the MediaEval 2015 Workshop, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01433209
Evaluation of Morphological Hierarchies for Supervised Segmentation, Proceedings of the 12th International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing, pp.39-50, 2015. ,
DOI : 10.1007/978-3-319-18720-4_4
URL : https://hal.archives-ouvertes.fr/hal-01142072
Unsupervised Speaker Identification in TV Broadcast Based on Written Names, IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.23, issue.1, pp.57-68, 2015. ,
DOI : 10.1109/TASLP.2014.2367822
URL : https://hal.archives-ouvertes.fr/hal-01060827
Robust tree-structured Named Entities Recognition from speech, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013. ,
DOI : 10.1109/ICASSP.2013.6639319
URL : https://hal.archives-ouvertes.fr/hal-00830142
Very deep convolutional networks for large-scale image recognition. arXiv preprint, 2014. ,
Particular object retrieval with integral max-pooling of CNN activations, Proceedings of the 2016 International Conference on Learning Representations, 2016. ,
Learning from labeled and unlabeled data with label propagation, 2002. ,