Speech Content Factorization
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Universal Speech Content Factorization
arXiv:2603.08977v2 Announce Type: replace-cross Abstract: We propose Universal Speech Content Factorization (USCF), a simple and invertible linear method for extracting a low-rank speech representation in which speaker timbre is suppressed while phonetic content is preserved. USCF extends Speech Content Factorization, a closed-set voice conversion (VC) method, to an open-set setting by learning a universal speech-to-content mapping via least-squares optimization and deriving speaker-specific...
Federating Governance: How Community Rules Scale with Mastodon Instances
Announce Type: replace Abstract: The rise of decentralized social media platforms like Mastodon and Bluesky highlights the challenge of scaling self-governance and moderation. As communities grow, they face new issues that demand increasingly complex governance structures. However, as moderation is mainly volunteer-driven, there is limited formal guidance on how community rules and moderation practices should evolve with growth.
Federating Governance: How Community Rules Scale with Mastodon Instances
arXiv:2606.05069v1 Announce Type: new Abstract: The rise of decentralized social media platforms like Mastodon and Bluesky highlights the challenge of scaling self-governance and moderation. As communities grow, they face new issues that demand increasingly complex governance structures. However, as moderation is mainly volunteer-driven, there is limited formal guidance on how community rules and moderation practices should evolve with growth.
UniVoice: A Unified Model for Speech and Singing Voice Generation
arXiv:2606.05852v1 Announce Type: new Abstract: Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirements on the generation process. Speech generation relies on flexible, language-driven prosody, whereas singing generation requires explicit melody control and accurate rhythmic alignment. This mismatch makes it challenging to train a single model that can generate both natural speech and...
The lawsuits that could give AI its ‘Big Tobacco’ moment
The legal strategy that hammered the tobacco industry and inspired a cascade of social media lawsuits is posing a rising threat to artificial intelligence companies. That threat got its boldest example Monday when Florida Republican Attorney General James Uthmeier sued OpenAI and CEO Sam Altman, alleging in part that ChatGPT is a dangerous product for users’ mental health and public safety. The suit is a novel use of product liability law for AI — and it parallels a legal strategy that...
Elon Musk is steamrolling Wall Street to become a trillionaire
Today on Decoder, I’m talking to Ryan Mac, a technology reporter at The New York Times and coauthor of the excellent book Character Limit: How Elon Musk Destroyed Twitter, which came out in 2024. I can’t recommend it enough. I wanted to have Ryan on the show because we’re on the cusp of the SpaceX IPO, which promises to be one of the most consequential public offerings in history for a variety of reasons — its biggest-ever size, of course, at nearly $2 trillion dollars, but also because all...
Australians have a lot in common with the Pope when it comes to AI
analysis What do the Pope and most Australians have in common? Neither trust AI companies Thu 4 Jun 2026 at 5:00am It's not often that the Pope, college students and Australians agree. One topic that has put these unusual bedfellows all roughly on the same page is artificial intelligence.