Metraipolis › archive › dc_3f3abbc53da5

HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing — arXiv:2611.03735

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03735
License (as archived)
CC0-1.0
Archived
2026-11-04T18:35:37.971Z
SHA-256 of the archived text
4ef2cd6464500cf07eda6667660dffe7fb3a08f18d1b17c49c04b25a0d3a6d6f
Stable URL of this page
https://metraipolis.com/documento/dc_3f3abbc53da5

How to cite

HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing — arXiv:2611.03735 — arXiv (en), https://arxiv.org/abs/2611.03735 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f3abbc53da5 (Metraipolis archive dc_3f3abbc53da5, sha256 4ef2cd6464500cf07eda6667660dffe7fb3a08f18d1b17c49c04b25a0d3a6d6f)
BibTeX
@misc{dc3f3abbc53da5,
  title = {HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing — arXiv:2611.03735},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03735},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f3abbc53da5; sha256 4ef2cd6464500cf07eda6667660dffe7fb3a08f18d1b17c49c04b25a0d3a6d6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03735. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present HyVox, a hybrid neuromorphic--von Neumann system for low-energy open-set speaker identification under tight energy budgets. HyVox splits the workload at the speaker embedding. A neuromorphic processor embeds the speech with sparse, event-driven computation, and a von Neumann microcontroller holds the speaker gallery and makes every decision: it scores queries by cosine similarity, rejects unknown speakers, and enrolls new users by writing a prototype, with no weight update. On the neuromorphic processor, a hierarchical temporal abstraction (HTA) SNN backbone learns a synaptic time constant per leaky integrate-and-fire (LIF) neuron, allocating 832 neurons across fast, medium, and slow timescales. A 32-neuron spiking embedding extractor (SEE), pretrained on episodes that each enroll new speakers and reject outsiders, turns the backbone output into an embedding for speakers unseen in training; its 32 spike counts are the only interface between the two processors. To fit the chip's synapse and integer budgets, we compress the backbone 6.5x to 29.0k synapses, train it for integer bit-shift dynamics, and fine-tune it with chip-accurate spiking training (CAST). CAST trains through a differentiable replica of the chip's integer neuron update, derived from its cycle-accurate simulator, so that gradient descent optimizes the exact weights and thresholds the chip runs; it doubles the top-1 accuracy of the mapped backbone on unseen speakers. On 20 Common Voice households of unseen speakers, HyVox reaches 99.6\% top-1 and 5.5\% rejection EER with 2 members and 94.9\% and 13.2\% with 20, and the network deployed on the neuromorphic chip matches its trained model. Each inference on a 3-s window takes 0.96 s and 1.63 mJ of dynamic energy, 42\% lower latency than the fastest embedded ANN baseline and 13.5x less dynamic and 5.8x less total energy than the most energy-efficient one.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2611.03735 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:32:37.379Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).