Researchers developed CircuitTree, a data structure built on a Ξ(N log N) tree-compose schedule, to compose arbitrarily many neural circuits into a single model, according to an arXiv paper (2610.1252β¦
A parameter-matched study using a frozen HuBERT backbone found that a 64-dimensional prosody representation trained to predict log F0, voicing, Delta log F0, log energy, and spectral tilt produced no β¦
Developer mchinen released Tape Heads, an open-source sonification system that plays back the attention patterns of audio transformer encoders including wav2vec 2.0, MuQ, and HuBERT, converting which β¦
A developer has built Psycho-Acoustic, a mental health monitoring tool that uses the HuBERT model, HuggingFace Transformers, and Librosa to quantify emotional states from non-verbal acoustic features.β¦
Researchers found that best-of-N text-to-speech evaluation is confounded by alignment between ASR verifier and evaluator families, with same-family pairs recovering 2-3Γ more oracle headroom than crosβ¦