Matteo Testa

3 papers · 2020–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze

Venues

ACL (1) ECCV (1) EMNLP (1)

Top co-authors

Jurgen Van De Walle (2) Giuseppe Ruggiero (2) Luigi Di Caro (2) Enrico Magli (1) Arslan Ali (1) Tiziano Bianchi (1)

Research topics

Deep Learning (2) Machine Learning (2) Speech & Audio (2) Learning Types · Machine Learning (2) Analysis (1) Core Methods (1) Learning Types · Deep Learning (1) Models (1) Synthesis (1) Techniques (1)

Keywords

self-supervised learning (2) voice conversion (2) cross-lingual fine-tuning (1) speech representation (1) speaker disentanglement (1) linear decomposition (1) speaker identity removal (1) polyglot voice (1) representation learning (1) any-to-one conversion (1) speech synthesis (1)

Papers

Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation ACL 2025 Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion EMNLP 2024 BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions ECCV 2020