Dayana Ribas
Research Scientist
ViVoLab, Aragón Institute for Engineering Research (I3A)
University of Zaragoza, Spain
Scientific researcher in the field of machine learning and statistical data analysis applied to speech signals and audio. In 2008 she graduated with honors from the Technological University of Havana with B.S. and M.S. degrees in Telecommunications Engineering. Then she was a research candidate in the Speech Processing Group of the Advanced Technologies Application Center (CENATAV), Havana, Cuba. Received the Ph.D. degree in 2016 from the Technological University of Havana, in the framework of international research collaboration actions with Zaragoza University, Spain, and INRIA, France.
She has achieved international development in the field of Speech Processing with state-of-the-art results. In 2016 she was Chair-Person at the Interspeech Conference, San Francisco, USA. In collaboration with Dr. Emmanuel Vincent and Dr. John Hansen, she organized a Special Session for “Realism in Speech Processing" in the framework of Interspeech 2016. Then she was guest Editor in the following Special Issue in Elsevier's Speech Communication Journal. In 2016 she was a postdoctoral fellow with the Multispeech team at INRIA, France and in 2018 she was visiting researcher at the University of Eastern Finland (UEF). Since 2018 she is research scientist with VIVOLAB, University of Zaragoza. She usually serves in the scientific committee of conferences and journals specialized in Speech Processing (ICASSP, Interspeech, EUSIPCO, ASRU, Elsevier-DSP, Speech Communication, Transactions of IEEE, etc).
Skilled in Speech Processing, Machine Learning, Statistics, and Data Analysis. Her research experience expands through the robust speech processing field, focusing mainly on robust speech processing, speaker recognition in noisy environments, realism in speech and language processing, and speech quality measures.
Publications
2021
Proceedings of XI Jornadas en Tecnología del Habla and VII Iberian SLTech (Iberspeech), vol. 2021-March, 2021.
Progressive Loss Functions for Speech Enhancement with Deep Neural Networks Artículo de revista
En: EURASIP Journal on Audio, Speech, and Music Processing, vol. 2021, no. 1, pp. 1-16, 2021.
2020
Knowledge Distillation and Random Erasing Data Augmentation for Text-Dependent Speaker Verification Conferencia
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 2020-May, 2020.
2019
Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), vol. 2019-September, 2019.
Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), vol. 2019-September, 2019.
