This version introduces Max 9 compatibility, a redesigned user interface, multi-label corpus building, and new label handling for filtering and real-time control. Max 9 Compatibility Somax2 now runs on Max 9.0.3 or later (earlier versions of Max 9 contained a bug in groove~ and buffer~ that caused issues with corpus loading). Updated User Interface Somax2’s interface has been redesigned and updated […]
ERC COSMOS is pleased to partner with ERC REACH in a demonstration-performance to set the stage for a panel discussion and a performance on AI’s impact on art creation, at the Night of Ideas at the Institut Français du Royaume-Uni (17 Queensberry Place London SW7 2DT)on 6 February at 19h20-20h10 in Les Salons. The event is free and open to the public with registration. […]
William Teixeira, Marco Fiorini, Mikhail Malt, Gérard Assayag. The Application of Somax2 in the Live-Electronics Design of Roberto Victório’s Chronos IIIc. Musica Hodie, 2024, 24, ⟨10.5216/mh.v24.78611⟩. ⟨hal-04760169⟩ Wililam Teixeira : » Excited to share one of the big research achievements I could be part of. It was just published in Musica Hodie the article concerning « The Application of […]
Marco Fiorini is giving two Somax2 workshop in Prague (CZ), on 12 December 2024 at Kampus Hybernská and on 13 December 2024 at Punctum, followed by a concert featuring Michal Wróblewski on sax, and Jonas Gerigk on doublebass.The trio will present works from their album Paragliding, published in 2023 for Ma Records. Paragliding by Gerigk […]
Master Class Somax2 au Conservatoire de Strasbourg par Gérard Assayag, Marco Fiorini Mikhail Malt et Georges Bloch de l’IRCAM à l’invitation de Tom Mays du 4 au 6 décembre. https://www.hear.fr/agenda/somax2/ Les étudiants et étudiantes ont pu découvrir Somax2, le prendre en main, apprendre à jouer avec, composer avec, enregistrer des corpus, avec un concert de […]
By Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov, Farinaz Koushanfar, Julian McAuley Sat, 30 Jan 2021 Read full publication Abstract: Voice cloning is the task of learning to synthesize the voice of an unseen speaker from a few samples. While current voice cloning methods achieve promising results in Text-to-Speech (TTS) synthesis for a new voice, these […]
