A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
Sylber: Syllabic embedding representation of speech from raw audio
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
SAND creates a new annotated speech dataset and open challenge to benchmark AI models for automatic early identification and progression prediction of ALS using voice signals.
citing papers explorer
-
A framework for analyzing concept representations in neural models
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
-
SAND: The Challenge on Speech Analysis for Neurodegenerative Disease Assessment
SAND creates a new annotated speech dataset and open challenge to benchmark AI models for automatic early identification and progression prediction of ALS using voice signals.
- FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates