AudioAI

Stronger Song IDs for the TikTok Era

Kari Jaaskelainen

10 Nov 2025 — 1 min read

Remixes, sped-up clips, and heavy compression make it hard to trace where music on social platforms comes from. This study introduces more robust neural audio fingerprints—compact “IDs” for audio—that can still recognize a song after it’s been distorted.

Music-first brains: Instead of training from scratch, the model uses pretrained music foundation models (like MuQ and MERT) as its backbone.
Trained for real-world messiness: Heavy data augmentation teaches the system to handle time-stretching, pitch shifts, compression, and filtering.
Proven gains: It consistently outperforms leading methods (NAFP, GraFPrint) and can match segments of audio, helping pinpoint where in a track a match occurs.

Why it matters: more reliable song identification supports creators, labels, and platforms with accurate attribution, catalog management, and rights protection—even when audio is altered.

Read: http://arxiv.org/abs/2511.05399v1

Paper: http://arxiv.org/abs/2511.05399v1

Register: https://www.AiFeta.com

AudioAI MusicTech AI Copyright AudioFingerprinting TikTok MachineLearning DigitalMedia

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)