HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing
cs.NE, cs.AI, cs.LG, cs.SD
Submitted: 2026-11-01
Updated: 2026-11-01
Project page: https://rethinking-ai.github.io/assets/papers/37_SpikeFit_Towards_Optimal_De.pdf
Terminology
Sources
- Small footprint Text-Independent Speaker Verification for Embedded Systems
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Micro-power spoken keyword spotting on Xylo Audio 2
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- Utterance-level Aggregation For Speaker Recognition In The Wild
- Hello Edge: Keyword Spotting on Microcontrollers
- To prune, or not to prune: exploring the efficacy of pruning for model compression
Related papers
- Evolutionary Ensemble of Agents
- EvoDR: Evolving Dispatching Rules via Large Language Model for Dynamic Flexible Assembly Flow Shop Scheduling
- RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics
- Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
- Design and Analysis of Temporal Representations in Neural Networks
- Evolutionary Computation: A Paradigm of Natural Generative AI and Creative Synthesis