Academia

PhD student at the Music Technology Group (MTG), Universitat Pompeu Fabra, Barcelona, Spain, since 2026.

Research
Music and audio representation learning
Supervisor
Xavier Serra
Co-supervisor
Frederic Font
Funding
“la Caixa” Foundation doctoral fellowship

MTG announcement · Full list on Google Scholar

Selected publications

  1. 2025

    Unseen Speaker and Language Adaptation for Lightweight Text-To-Speech with Adapters

    Alessio Falai, Ziyao Zhang, Akos Gangoly

    IEEE MLSP 2025 · Istanbul, Turkey

  2. 2025

    Amazon Nova Sonic: Technical report and model card

    Amazon Artificial General Intelligence

    Technical report, Amazon

    I was one of the contributors.

  3. 2023

    Cross-Lingual Knowledge Distillation via Flow-Based Voice Conversion for Robust Polyglot Text-to-Speech

    Dariusz Piotrowski*, Renard Korzeniowski*, Alessio Falai*, Sebastian Cygert, Kamil Pokora, Georgi Tinchev, Ziyao Zhang, Kayoko Yanagisawa* Equal contribution

    ICONIP 2023 · Changsha, China

  4. 2022

    Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)

    Ariadna Sanchez, Alessio Falai, Ziyao Zhang, Orazio Angelini, Kayoko Yanagisawa

    Interspeech 2022 · Incheon, South Korea

  5. 2022

    Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)

    Ziyao Zhang, Alessio Falai, Ariadna Sanchez, Orazio Angelini, Kayoko Yanagisawa

    Interspeech 2022 · Incheon, South Korea

Theses

  1. 2022

    Conditioning text-to-speech synthesis on dialect accent: a case study

    Alessio Falai

    MSc thesis in Artificial Intelligence · University of Bologna