Publications

@conference{Gimeno2020pauc,

title = {Partial AUC Optimisation Using Recurrent Neural Networks for Music Detection with Limited Training Data},

author = {Pablo Gimeno and Victoria Mingote and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},

doi = {10.21437/Interspeech.2020-1108},

year  = {2020},

date = {2020-10-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

volume = {2020-October},

pages = {3067--3071},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Mingote2020enrollment,

title = {Training Speaker Enrollment Models by Network Optimization},

author = {Victoria Mingote and Antonio Miguel and Alfonso Ortega and Eduardo Lleida},

doi = {10.21437/Interspeech.2020-2325},

year  = {2020},

date = {2020-10-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

volume = {2020-October},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Prieto2020,

title = {Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions},

author = {Santi Prieto and Alfonso Ortega and Iván López-Espejo and Eduardo Lleida},

doi = {10.21437/Interspeech.2020-1402},

year  = {2020},

date = {2020-10-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

volume = {2020-October},

pages = {1511--1515},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Mingote2020distillation,

title = {Knowledge Distillation and Random Erasing Data Augmentation for Text-Dependent Speaker Verification},

author = {Victoria Mingote and Antonio Miguel and Dayana Ribas and Alfonso Ortega and Eduardo Lleida},

doi = {10.1109/ICASSP40776.2020.9053153},

year  = {2020},

date = {2020-05-01},

booktitle = {Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

volume = {2020-May},

pages = {6824-6828},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Mingote2019language,

title = {Language recognition using triplet neural networks},

author = {Victoria Mingote and Diego Castan and Mitchell McLaren and Mahesh Kumar Nandwana and Alfonso Ortega and Eduardo Lleida and Antonio Miguel},

doi = {10.21437/Interspeech.2019-2437},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

journal = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

volume = {2019-September},

pages = {4025-4029},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Mingote2019optimization,

title = {Optimization of false acceptance/rejection rates and decision threshold for end-to-end text-dependent speaker verification systems},

author = {Victoria Mingote and Antonio Miguel and Dayana Ribas and Alfonso Ortega and Eduardo Lleida},

doi = {10.21437/Interspeech.2019-2550},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

journal = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},

volume = {2019-September},

pages = {2903-2907},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Viñals2019nist,

title = {Phonetically-aware embeddings, wide residual networks with time-delay neural networks and self attention models for the 2018 NIST speaker recognition evaluation},

author = {Ignacio Viñals and Dayana Ribas and Victoria Mingote and Jorge Llombart and Pablo Gimeno and Antonio Miguel and Alfonso Ortega and Eduardo Lleida},

doi = {10.21437/Interspeech.2019-2417},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

journal = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

volume = {2019-September},

pages = {4310-4314},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Llombart2019progressive,

title = {Progressive speech enhancement with residual connections},

author = {Jorge Llombart and Dayana Ribas and Antonio Miguel and Luis Vicente and Alfonso Ortega and Eduardo Lleida},

doi = {10.21437/Interspeech.2019-1748},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

journal = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},

volume = {2019-September},

pages = {3193-3197},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Llombart2019residual,

title = {Speech enhancement with wide residual networks in reverberant environments},

author = {Jorge Llombart and Dayana Ribas and Antonio Miguel and Luis Vicente and Alfonso Ortega and Eduardo Lleida},

doi = {10.21437/Interspeech.2019-1745},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

journal = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},

volume = {2019-September},

pages = {1811-1815},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Viñals2019dihard,

title = {Vivolab speaker diarization system for the Dihard 2019 challenge},

author = {Ignacio Viñals and Pablo Gimeno and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},

doi = {10.21437/Interspeech.2019-2462},

year  = {2019},

date = {2019-01-01},

booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)},

journal = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},

volume = {2019-September},

pages = {988-992},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Gimeno2018recurrent,

title = {A Recurrent Neural Network Approach to Audio Segmentation for Broadcast Domain Data},

author = {Pablo Gimeno and Ignacio Viñals and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},

doi = {10.21437/IberSPEECH.2018-19},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of X Jornadas en Tecnología del Habla and VI Iberian SLTech (Iberspeech)},

volume = {2018-November},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Viñals2018,

title = {In-domain Adaptation Solutions for the RTVE 2018 Diarization Challenge},

author = {Ignacio Viñals and Pablo Gimeno and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},

doi = {10.21437/IberSPEECH.2018-45},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of X Jornadas en Tecnología del Habla and VI Iberian SLTech (Iberspeech)},

volume = {2018-November},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Mingote2018,

title = {Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification},

author = {Victoria Mingote and Antonio Miguel and Alfonso Ortega and Eduardo Lleida},

doi = {10.21437/IberSPEECH.2018-1},

year  = {2018},

date = {2018-01-01},

booktitle = {Proceedings of X Jornadas en Tecnología del Habla and VI Iberian SLTech (Iberspeech)},

volume = {2018-November},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}