Paolo Sani

According to our database, Paolo Sani authored at least 5 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Bridging the Training-Inference Gap in TTS: Training Strategies for Robust Generative Postprocessing for Low-Resource Speakers.

Frank Zalkow, Paolo Sani, Kishor Kayyar Lakshminarayana, Emanuël A. P. Habets, Nicola Pia, Christian Dittmar

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

2024

PAD-VC: A Prosody-Aware Decoder for Any-to-Few Voice Conversion.

Arunava Kr. Kalita, Christian Dittmar, Paolo Sani, Frank Zalkow, Emanuël A. P. Habets, Rusha Patra

Proceedings of the 18th International Workshop on Acoustic Signal Enhancement, 2024

2023

ITTV - A Dataset of Italian Television for Automatic Genre Classification.

Paolo Sani, Alessandro Ilic Mezza, Augusto Sarti

Dataset, June, 2023

Automatic TV Genre Classification Based on Visually-Conditioned Deep Audio Features.

Alessandro Ilic Mezza, Paolo Sani, Augusto Sarti

Proceedings of the 31st European Signal Processing Conference, 2023

The AudioLabs System for the Blizzard Challenge 2023.

Frank Zalkow, Paolo Sani, Michael Fast, Judith Bauer, Mohammad Joshaghani, Kishor Kayyar Lakshminarayana, Emanuël A. P. Habets, Christian Dittmar

Proceedings of the 18th Blizzard Challenge Workshop, Grenoble, France, August 29, 2023, 2023