テクノロジー
Meta、音源編集の“Photoshop”「SAM Audio」を発表：「何でも分割する」AIの最終ピースとは
Meta Platforms（以下、Meta）は2025年12月16日、音声処理のパラダイムシフトとなる画期的なAIモデル、「SAM Audio（Segment Anything Model for Audio）」を発表 […]
Tech Product
Demucs
Overview
最終更新: 2026年7月9日Demucsは、Meta AI（旧Facebook AI）が開発したオープンソースの音楽分離ソフトウェア
Mentioned Articles
1 件External Mentions
9 件- arXiv DTT-BSR+: A Generative-Regression Cascade for Music Source Restoration
- arXiv Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization
- arXiv Zero-Shot TTS With Enhanced Audio Prompts: Bsc Submission For The 2026 Wildspoof Challenge TTS Track
- arXiv Where Does Speech Enhancement Adapt? Probing Study Under Controlled Degradation
- arXiv Optimizing Neural Architectures for Hindi Speech Separation and Enhancement in Noisy Environments
- arXiv Adaptive Slimming for Scalable and Efficient Speech Enhancement
- Hacker News DigitalOcean acquires Paperspace (YC W15) for $111M in cash
- Hacker News Show HN: Debucsser, CSS debugging made easy
- Hacker News De-Muslimization: Flying while Muslim after the travel ban