findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding
cs.CL, cs.AI
Submitted: 2026-03-27
Updated: 2026-06-15
Code: https://github.com/hjvm/findsyllshttps:
Terminology
Sources
- Towards Unsupervised Speech Recognition at the Syllable-Level
- Scaling Spoken Language Models with Syllabic Speech Tokenization
- Unsupervised lexicon learning from speech is limited by representations rather than clustering
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
- Speech Model Pre-training for End-to-End Spoken Language Understanding
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data