Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #9457

keyword spotting

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

RESEARCH · 1 SOURCE · arXiv cs.AI

Paper proposes "Model as a Library" on-device speech architecture for low-resource African languages

The arXiv preprint (arXiv:2609.38574v1) introduces Model as a Library (MaaL), a system-design and position paper that packages small, community-enrolled speech models as versioned on-device dependencies to enable offline structured data collection. MaaL relies on closed‑vocabulary keyword spotting with vocabularies enrolled from a few example recordings by speakers at deployment and proposes transpiling existing closed‑vocabulary digital forms into MaaL schemas; the paper provides an analytical feasibility case and lists requirements for a working implementation.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

TGL-NSGA-II: teacher-guided low-fidelity NAS for TinyML (arXiv:2609.30553v1)

arXiv:2609.30553v1 introduces TGL-NSGA-II, a low-fidelity framework for constrained TinyML neural architecture search that uses a pretrained teacher to stratify samples and a short KD-Lite distillation plus a Gaussian-process surrogate to score candidates. The paper reports improved proxy ranking (Kendall-τ 0.74 and 0.62 on keyword spotting and bird-call tasks), a 41% reduction in proxy-score variance versus random evaluation, better multi-objective search metrics under a fixed budget, and 2.2x faster runs than full NSGA-II, while noting the guarantees apply to population-level low-fidelity evaluation and do not prove full evolutionary convergence.

6.0