{
  "abstract": "Spiking Neural Networks (SNNs) promise energy-efficient inference through sparse, event-driven computation, yet remain constrained on continuous, context-dependent tasks such as automatic speech recognition (ASR). A key bottleneck is the Leaky Integrate-and-Fire (LIF) neuron, whose membrane decay erases information across pauses and phonetic boundaries while it must both extract features and retain long-range context. Inspired by cortical separation of nonlinear filtering and somatic integration, we introduce the Spiking Ternary GRU (stGRU): a ternary-weight gated recurrent unit performs temporal filtering, while downstream Resonate-and-Fire (RF) neurons generate the binary spike stream driving the next block's event pathway. This makes binary event transmission a native training constraint rather than a separate deployment-time activation quantization step; together with ternary weights, learned projections avoid dense floating-point matrix MACs. Trained end-to-end on LibriSpeech-960, Small, Medium, and Large stGRUs reach 8.09%, 7.04%, and $6.44 \\pm 0.17\\%$ WER on test-clean without an external language model. To our knowledge, these are the first matrix-MAC-free spiking networks without a learned ANN sequence decoder to achieve single-digit WER on LibriSpeech. The architecture also achieves 10.88% test CER on Aishell-1 (9.28% on dev) when trained from scratch. Internally, trained networks develop a depth-graded hierarchy: shallow layers act as fast acoustic filters, while deep layers form slower semantic integrators whose latent representations segregate into part-of-speech manifolds and word-level spike events. Deep-layer firing rates follow lognormal distributions with a sparsity gradient, mirroring hierarchical processing observed in human cortex in vivo. Our biologically grounded architecture combines competitive ASR with favorable modeled compute and memory cost.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.29720",
  "author_total": 4,
  "authors": [
    {
      "name": "Pavlos Poulos"
    },
    {
      "name": "Katelyn Sadorf"
    },
    {
      "name": "Themos Stafylakis"
    },
    {
      "name": "Costas A. Anastassiou"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/btqf1k99k2kp9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.29720",
  "fulltext_url": null,
  "id": "btqf1k99k2kp9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.29720",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "cs.SD"
    ],
    [
      "arxiv",
      "eess.AS"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "1702|Speech Recognition and Synthesis"
    ]
  ],
  "openalex": "W7223254503",
  "pdf_url": "https://arxiv.org/pdf/2610.29720",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/btqf1k99k2kp9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:20Z",
      "native_id": "2610.29720",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.29720"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition",
  "title_text": "Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:20Z",
  "url": "https://research.draconitic.com/paper/btqf1k99k2kp9",
  "venue": "arXiv",
  "versions": []
}