{
  "abstract": "Brain-computer interfaces (BCIs) offer a promising solution to speech loss due to neurological injury by decoding intended speech directly from brain activity. While recent BCIs have restored high-accuracy text-based communication, they fail to provide instantaneous voice output essential for the natural flow of conversation. Brain-to-voice BCIs address this gap by decoding voice directly from neural signals. However, even the state-of-the-art (SOTA) BCI-synthesized voice is not yet intelligible enough for real-world adoption. We introduce brain2voice 2.0, a new multimodal Transformer-based BCI decoder architecture capable of synthesizing highly intelligible voice from intracortical neural signals in real-time. Brain2voice 2.0 is trained on continuous and custom-tokenized acoustic targets and phoneme targets, leveraging their complementary speech information. We use self-supervised and adversarial training objectives that enhance acoustic feature quality and improve synthesis intelligibility. At each 10 ms timestep, the model causally outputs continuous and tokenized acoustic features for real-time voice synthesis as well as time-aligned phoneme predictions (raw phoneme error rate: 7%, comparable to the latest brain-to-text models). We evaluated this new approach on our prior intracortical brain-to-voice benchmark dataset (Wairagkar et al. 2025). Naive human listeners transcribed brain2voice 2.0 synthesized voice with a word error rate of 5.24%--an 8x improvement in intelligibility over previous SOTA results (43.75%). Brain2voice 2.0 demonstrates that highly intelligible real-time voice synthesis from neural signals is achievable, for the first time crossing the intelligibility threshold necessary for clinically viable brain-to-voice BCIs for people with paralysis.",
  "abstract_shown": true,
  "affiliations": [
    "University of California, Davis"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "M. Wairagkar"
    },
    {
      "name": "A. Srinivasan"
    },
    {
      "name": "N. S. Card"
    },
    {
      "name": "T. Singer-Clark"
    },
    {
      "name": "X. Hou"
    },
    {
      "name": "C. Iacobacci"
    },
    {
      "name": "L. M. Miller"
    },
    {
      "name": "L. R. Hochberg"
    },
    {
      "name": "D. M. Brandman"
    },
    {
      "name": "S. D. Stavisky"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c63cf7fxp9wzy.bib",
  "cited_by": 2,
  "doi": "10.64898/2026.06.30.735633",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.06.30.735633v2.full",
  "id": "c63cf7fxp9wzy",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.06.30.735633v2",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "neuroscience"
    ],
    [
      "openalex",
      "2805|EEG and Brain-Computer Interfaces"
    ]
  ],
  "openalex": "W7167455010",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.06.30.735633v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c63cf7fxp9wzy.ris",
  "sources": [
    {
      "first_seen": "2026-11-14T00:20:44Z",
      "native_id": "10.64898/2026.06.30.735633",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.06.30.735633v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Brain2voice 2.0: High-performance voice synthesis brain-computer interface",
  "title_text": "Brain2voice 2.0: High-performance voice synthesis brain-computer interface",
  "type": "preprint",
  "updated_at": "2026-11-14T00:20:44Z",
  "url": "https://research.draconitic.com/paper/c63cf7fxp9wzy",
  "venue": "bioRxiv",
  "versions": []
}