OSCR

Shared latent representations of speech production for cross-patient speech decoding.

Code ↔ Paper

23 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 23 matches
  1. [1] § Methods › Pitch subsampling ↔ aligned_decoding/processing_utils/poisson_disk_sampling.py, lines 9–82 · score 0.82 · Poisson disk sampling, desired pitch, subsampled electrodes, select electrodes
  2. [2] § Methods › Connectionist temporal classification recurrent neural network (CTC-RNN) decoding ↔ aligned_decoding/realtime_sim/realtime_nn_model.py, lines 101–150 · score 0.76 · stacked RNN model, sliding window, CTC loss, blank, stride, classification
  3. [3] § Results › Cross-patient alignment improves speech decoding in a simulated real-time environment ↔ aligned_decoding/scripts/train_ctc_rnn.py, lines 1–55 · score 0.72 · phoneme error rate, CTC RNN model, neural recording, phoneme sequences, speech decoding, loss
  4. [4] § Methods › Simulated real-time data generation ↔ aligned_decoding/realtime_sim/realtime_processing.py, lines 10–39 · score 0.72 · Bandpass filtering, High gamma, RMS, bins, power, bands
  5. [5] § Methods › Alignment of latent dynamics ↔ aligned_decoding/alignment/AlignCCA.py, lines 11–119 · score 0.71 · canonical correlations, target space, patient space, CCA alignment, latent dynamics, target patient
  6. [6] § Methods › Cross-patient projection ↔ aligned_decoding/alignment/JointPCA.py, lines 13–162 · score 0.70 · transformation matrices, PCA transform, PCA decomposition, latent space, optionally, components
  7. [7] § Results › High-resolution and broad coverage are critical to alignment ↔ aligned_decoding/processing_utils/poisson_disk_sampling.py, lines 9–82 · score 0.70 · Poisson disk sampling, sampled electrodes, pitch subsampled, mm, decoding
  8. [8] § Methods › Connectionist temporal classification recurrent neural network (CTC-RNN) decoding ↔ aligned_decoding/realtime_sim/realtime_datamodule.py, lines 578–724 · score 0.67 · dimensionality reduction, latent space, source patient, post, truncated, aligned cross patient
  9. [9] § Methods › High-gamma extraction ↔ aligned_decoding/realtime_sim/realtime_processing.py, lines 10–39 · score 0.66 · bandpass filtered signals, high gamma, Channels, neural, decoding
  10. [10] § Results › Cross-patient alignment preserves spatial articulator maps ↔ aligned_decoding/figure_analyses/supp/supp_fig_9.ipynb, lines 1241–1271 · score 0.64 · unaligned reconstruction, aligned reconstructed, cross patient speech, cross patient decoding, decoding accuracies, TME
  11. [11] § Methods › Cross-patient projection ↔ aligned_decoding/scripts/aligned_decode_svm.py, lines 74–115 · score 0.63 · bagged SVM classifier, fold cross validation, PCA, Cross patient, accuracy, trained
  12. [12] § Methods › Alignment of latent dynamics ↔ aligned_decoding/nn_models/data_utils/AlignCCA.py, lines 11–105 · score 0.62 · canonical correlations, target space, CCA alignment, latent dynamics, target patient, mapping
  13. [13] § Methods › Connectionist temporal classification recurrent neural network (CTC-RNN) decoding ↔ aligned_decoding/scripts/tune_ctc_rnn.py, lines 638–685 · score 0.61 · Hyperparameter optimization, CTC RNN, cross validation, target patient, fit, aligned decoding
  14. [14] § Methods › Connectionist temporal classification recurrent neural network (CTC-RNN) decoding ↔ aligned_decoding/scripts/tune_ctc_rnn_align.py, lines 581–628 · score 0.61 · Hyperparameter optimization, CTC RNN, cross validation, target patient, fit, aligned decoding
  15. [15] § Methods › Single-electrode articulator tuning ↔ aligned_decoding/scripts/aligned_decode_svm_ncv.py, lines 323–394 · score 0.59 · nested cross validation, linear discriminant, splitting, predict, fold, classify
  16. [16] § Methods › Single-electrode articulator tuning ↔ aligned_decoding/scripts/aligned_decode_grid_subsample.py, lines 271–340 · score 0.58 · nested cross validation, linear discriminant, splitting, predict, fold, classify
  17. [17] § Results › Cross-patient alignment improves speech decoding in a simulated real-time environment ↔ aligned_decoding/realtime_sim/realtime_nn_model.py, lines 101–150 · score 0.57 · sliding windows, error rate, RNN model, loss, classification, CTC
  18. [18] § Methods › Cross-patient projection ↔ aligned_decoding/scripts/aligned_decode_spatialAvg_subsample.py, lines 239–312 · score 0.56 · class weight, cross validation, bagged, kernel, predictions, folds
  19. [19] § Methods › Cross-patient phoneme decoding ↔ aligned_decoding/decoders/cross_pt_decoders.py, lines 89–180 · score 0.56 · latent dimensionality, cross patient sources, truncated, concatenated, variance, target patient
  20. [20] § Results › Cross-patient alignment preserves spatial articulator maps ↔ aligned_decoding/alignment/AlignCCA.py, lines 11–119 · score 0.56 · extract latent dynamics, CCA alignment, latent space, optionally, correlation, target patient
  21. [21] § Methods › Cross-patient projection ↔ aligned_decoding/figure_analyses/fig_3.ipynb, lines 693–763 · score 0.55 · ROC AUC, aligned reconstructions, compatibility, flattened, components, unaligned
  22. [22] § Methods › Latent dynamics extraction ↔ aligned_decoding/figure_analyses/fig_2.ipynb, lines 1037–1131 · score 0.55 · articulatory features, t-SNE, perplexity, latent dynamics, Silhouette, Clustering
  23. [23] § Methods › Latent dynamics extraction ↔ aligned_decoding/figure_analyses/supp/supp_fig_6_7.ipynb, lines 1044–1139 · score 0.55 · articulatory features, t-SNE, perplexity, latent dynamics, Silhouette, Clustering

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 255 lines · 9.1 KB · MIT · 2 matches

  1. """Poisson disk sampling for spatially uniform electrode subsampling."""
  3. import numpy as np
  4. import scipy.io as sio
  5. import matplotlib.pyplot as plt
  6. import time
  9. def pitch_subsample_sig_channels(pt, pitch, data_path):
  10. """Subsamples electrodes at a given pitch and returns significant indices.
  12. Uses Poisson disk sampling to select electrodes at the specified pitch
  13. (inter-electrode spacing in mm), then identifies which of the sampled
  14. electrodes are significant. Recursively retries if no significant
  15. channels are sampled.
  17. Args:
  18. pt (str): Subject identifier string.
  19. pitch (float): Desired inter-electrode pitch in millimeters.
  20. data_path (str): Root directory containing subject data folders.
  22. Returns:
  23. ndarray: Indices of significant channels within the subsampled set.
  24. """
  25. # load in channel map
  26. chanMap = sio.loadmat(f'{data_path}/{pt}/{pt}_channelMap.mat')['chanMap']
  28. # load in significant channel data
  29. sigChan = np.squeeze(
  30. sio.loadmat(f'{data_path}/{pt}/{pt}_sigChannel.mat')['sigChannel'])
  32. # trim nan edges if necessary
  33. if chanMap.shape[1] == 24:
  34. chanMap = chanMap[:,1:-1]
  36. # to preserve pitch when sampling across different grid sizes, calculate
  37. # number of electrodes to sample based on the desired pitch
  38. if pt in ['S14', 'S22', 'S23', 'S26']:
  39. mmX = 11.3
  40. mmY = 22.5
  41. maxElec = 128
  42. elif pt in ['S33', 'S39', 'S58', 'S62']:
  43. mmX = 37.8
  44. mmY = 20.6
  45. maxElec = 256
  46. nElec = round(mmX * mmY / pitch**2)
  48. if nElec >= maxElec:
  49. # just sample all electrodes if we're sampling more than the max
  50. elecPt = np.arange(1, maxElec+1)
  51. else:
  52. # parameters for poisson disk sampling
  53. gridX, gridY = chanMap.shape
  54. domain = (gridX, gridY)
  55. spacing = np.floor(np.sqrt(gridX * gridY / nElec))
  57. # do poisson disk sampling and -1 to get 0-indexed
  58. elecIdx = poisson_disk_sampling(domain, spacing, nElec)
  59. elecIdx = np.round(elecIdx).astype(int) - 1
  61. # convert 2D coordinates to channel numbers
  62. elecPt = chanMap[elecIdx[:, 0], elecIdx[:, 1]]
  63. elecPt = np.nan_to_num(elecPt, nan=-1).astype(int)
  65. # check if we need to sample more electrodes
  66. if elecPt.shape[0] < nElec and spacing == 1:
  67. nRemaining = nElec - elecPt.shape[0]
  68. # get unsampled electrodes
  69. remainingElecs = np.setdiff1d(np.arange(1, gridX * gridY+1), elecPt)
  70. # uniformly sample remaining electrodes
  71. extraSampPt = np.random.choice(remainingElecs, nRemaining,
  72. replace=False)
  73. elecPt = np.concatenate((elecPt, extraSampPt))
  75. # get indices of significant channels in the subsampled set
  76. _, sigIdx, _ = np.intersect1d(sigChan, elecPt, return_indices=True)
  78. # do sampling over if we don't sample at least 1 significant channel
  79. if len(sigIdx) == 0:
  80. return pitch_subsample_sig_channels(pt, nElec, data_path)
  82. return sigIdx
  84. def poisson_disk_sampling(domain, spacing, nPoints, threshold=60,
  85. showIter=False, maxIter=1000):
  86. """
  87. Poisson Disk Sampling algorithm. Adapted from MATLAB code by Mohak Patel
  88. (Brown University, 2016). Follows the algorithm in Bridson 2007
  89. (https://www.cs.ubc.ca/~rbridson/docs/bridson-siggraph07-poissondisk.pdf).
  90. """
  91. ##### Initialize the grid #####
  92. ndim = len(domain)
  93. cellSize = spacing / np.sqrt(ndim)
  95. # Construct grid
  96. sGrid = [np.arange(1, s + 1, cellSize) for s in domain]
  97. sGrid = np.meshgrid(*sGrid, indexing='ij')
  98. sizeGrid = sGrid[0].shape
  100. # Flatten grid points into array of coordinates
  101. sGrid = np.column_stack([g.ravel() for g in sGrid])
  103. emptyGrid = np.ones(sGrid.shape[0], dtype=bool)
  104. nEmptyGrid = np.sum(emptyGrid)
  105. scoreGrid = np.zeros_like(emptyGrid, dtype=int)
  107. ##### Dart-throwing #####
  108. ptsCreated = 0
  109. pts = []
  110. iter = 0
  112. start = time.time()
  113. while ptsCreated < nPoints and nEmptyGrid > 0:
  114. if iter > maxIter:
  115. print(f'Reached max iterations with {ptsCreated} points. Trying sampling again.')
  116. return poisson_disk_sampling(domain, spacing, nPoints, threshold)
  118. availGrid = np.where(emptyGrid)[0]
  119. dataPts = np.minimum(nEmptyGrid, nPoints)
  120. # sample nPoints from available grid points
  121. sampPts = np.random.choice(availGrid, dataPts, replace=False)
  122. # dart throws
  123. tempPts = sGrid[sampPts] + cellSize * np.random.rand(dataPts, ndim)
  125. ### Find good dart throws ###
  126. if len(pts) > 0:
  127. allPts = np.vstack((pts, tempPts))
  128. else:
  129. allPts = tempPts
  131. # get distance to nearest neighbor
  132. neighDist = min_neighbor_distance(allPts, tempPts)
  134. # check which points are valid
  135. inDomain = np.all(tempPts < domain, axis=1) # within domain
  136. goodSpacing = neighDist > spacing # far enough from other points
  137. validPts = inDomain & goodSpacing
  139. scorePts = tempPts[~validPts, :] # keep scores from bad throws
  140. tempPts = tempPts[validPts, :] # save good throws
  142. ### update tracking grids ###
  144. # update empty grid
  145. emptyPts = np.floor((tempPts + cellSize - 1) / cellSize).astype(int)
  146. # convert to linear index
  147. emptyPtIdx = np.ravel_multi_index(emptyPts.T-1, sizeGrid)
  148. # emptyPtIdx = np.ravel_multi_index((emptyPts[:,0], emptyPts[:,1]), sizeGrid)
  149. emptyGrid[emptyPtIdx] = False
  151. # update score grid
  152. scorePts = np.floor((scorePts + cellSize - 1) / cellSize).astype(int)
  153. scorePtIdx = np.ravel_multi_index(scorePts.T-1, sizeGrid)
  154. # scorePtIdx = np.ravel_multi_index((scorePts[:,0], scorePts[:,1]), sizeGrid)
  155. scoreGrid[scorePtIdx] += 1
  157. # update empty grid if score grid has exceeded threshold
  158. emptyGrid = emptyGrid & (scoreGrid < threshold)
  160. # update quantities for next iteration
  161. nEmptyGrid = np.sum(emptyGrid)
  162. pts.extend(tempPts)
  163. ptsCreated += tempPts.shape[0]
  164. iter += 1
  166. if showIter:
  167. elapsed = time.time() - start
  168. print(f"Iteration: {iter} Points Created: {ptsCreated} "
  169. f"EmptyGrid: {nEmptyGrid} Total Time: {elapsed:.3f}")
  171. # trim points to nPoints if more are created in last iteration
  172. pts = np.vstack(pts)
  173. if ptsCreated > nPoints:
  174. ptIdxs = np.random.choice(pts.shape[0], nPoints, replace=False)
  175. pts = pts[ptIdxs]
  176. return pts
  179. def min_neighbor_distance(pts, newPts):
  180. """Computes the distance from each new point to its nearest neighbor.
  182. Because ``newPts`` is a subset of ``pts``, the true nearest neighbor is
  183. the second closest point (the first is the point itself).
  185. Args:
  186. pts (ndarray): All existing points with shape (n, ndim).
  187. newPts (ndarray): Query points with shape (m, ndim), must be a
  188. subset of ``pts``.
  190. Returns:
  191. ndarray: Array of length m with the nearest-neighbor distance for
  192. each query point.
  193. """
  194. # find distances to nearest neighbors
  195. _, D = knn_search(pts, newPts, 2)
  196. # since pts and newPts will include the same points, nearest neighbor
  197. # distance will be the second index, since the first will be the point
  198. # itself
  199. return D[:, 1]
  202. def knn_search(pts, newPts, k):
  203. """Brute-force k-nearest-neighbor search.
  205. Args:
  206. pts (ndarray): Reference points with shape (n, ndim).
  207. newPts (ndarray): Query points with shape (m, ndim).
  208. k (int): Number of nearest neighbors to return.
  210. Returns:
  211. tuple: (I, D) where I is an (m, k) integer array of neighbor indices
  212. into ``pts`` and D is an (m, k) float array of corresponding
  213. Euclidean distances, both sorted by ascending distance.
  214. """
  215. m = newPts.shape[0]
  216. D = np.zeros((m, k))
  217. I = np.zeros((m, k), dtype=int)
  218. for i in range(m):
  219. dist = np.sqrt(np.sum((pts - newPts[i])**2, axis=1))
  220. I[i] = np.argsort(dist)[:k]
  221. D[i] = np.sort(dist)[:k]
  222. return I, D
  225. if __name__ == '__main__':
  226. # testing the grid sampling
  227. gridX = 8
  228. gridY = 16
  230. for nElec in [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 100]:
  232. print('### Sampling for nElec =', nElec, '###')
  233. # nElec =
  234. domain = (gridX, gridY)
  235. spacing = np.floor(np.sqrt(gridX * gridY / nElec))
  236. # print(spacing)
  238. n_grids = 3
  239. saved_grids = np.zeros((n_grids, gridX, gridY))
  240. for i in range(n_grids):
  241. points = poisson_disk_sampling(domain, spacing, nElec)
  242. points = np.round(points).astype(int) - 1
  243. print(f'Sampled {points.shape[0]} points')
  245. grid = np.zeros((gridX, gridY))
  246. grid[points[:, 0], points[:, 1]] = 1
  248. # plt.figure(figsize=(8, 8))
  249. plt.imshow(grid.T, cmap='gray', origin='lower')
  250. plt.show()
  251. saved_grids[i] = grid
  253. # check that the grids are different
  254. n_unique_grids = np.unique(saved_grids, axis=0).shape[0]
  255. print(n_unique_grids, n_unique_grids == n_grids)

poisson_disk_sampling.py at commit a70f1ae, under MIT · at the source

Overview

Authors: Z. Spalding1, S. Duraivel1,2, S. Rahimpour3,4, C. Wang1, K. Barth1, C. Schmitz1, S. P. Lad3, A. H. Friedman3, D. G. Southwell3,5,6, J. Viventi1,3,5,6, G. B. Cogan1,3,6,7,8
ORCID iDs: Z. Spalding, K. Barth, C. Schmitz, S. P. Lad, D. G. Southwell, J. Viventi, G. B. Cogan
  1. Department of Biomedical Engineering, Duke University,Durham, NC USA
  2. Present Address: McGovern Institute for Brain Research, Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology,Cambridge, MA USA
  3. Department of Neurosurgery, Duke School of Medicine,Durham, NC USA
  4. Present Address: Department of Neurosurgery, University of Utah,Salt Lake City, UT USA
  5. Department of Neurobiology, Duke School of Medicine,Durham, NC USA
  6. Duke Comprehensive Epilepsy Center, Duke University,Durham, NC USA
  7. Department of Neurology, Duke School of Medicine,Durham, NC USA
  8. Center for Cognitive Neuroscience, Duke University,Durham, NC USA
Institutions: Duke University (United States); Massachusetts Institute of Technology (United States); University of Utah (United States)
Journal: Nature communications, volume 17, issue 1, article 8716
Dates: received 1 September 2025; accepted 1 July 2026; published online 16 July 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41467-026-75455-1 · PMID 42463660 · PMCID PMC13490415 · OpenAlex W4413425109
Open access: gold, a free copy (OpenAlex)
Preprint: doi:10.1101/2025.08.21.671516
Status: code verified
Categories: intracranial EEG (iEEG / ECoG / SEEG) (modality), human (organism), cognitive (subfield)
Methods: Spectral & time-frequency, Connectivity, Statistics, Smoothing, state filtering, decompositions, Machine learning, Preprocessing
Keywords: Brain-machine interface, Motor cortex, Language
MeSH: Brain-Computer Interfaces*, Speech*, Adult, Brain, Electrocorticography, Female, Humans, Male (* major topic)
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: National Institute on Deafness and Other Communication Disorders (R01DC019498); Congressionally Directed Medical Research Programs (CDMRP) (W81XWH-21-0538); NINDS (R01NS129703, UG3NS120172)
Citations: cited by 1 paper (Europe PMC); 55 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repositories

Its files are read in the Code ↔ Paper reader above, with 23 matches between paragraphs and lines of code.

gamaleldin/TME

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: ad1adf835e72dbba012406b5a3af30701adc8993, 8 September 2017
Languages: MATLAB (13), C/C++ (8), C++ (8)
Size: 40 files, 29 scripts
Software Heritage: not archived
Found in: the text, “Generation of surrogate data”
Holds: README, tests
Not found: license file, CITATION.cff, environment file, continuous integration, documentation
Tools: Statistics and Machine Learning Toolbox (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
30 files
At the source: github.com/gamaleldin/TME

coganlab/cross_patient_speech_decoding

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: a70f1ae711cf3627cf9357d2a72868a74f2d774f, 3 June 2026
Languages: Python (45), Jupyter (29)
Size: 83 files, 74 scripts
Software Heritage: not archived
Found in: “Code availability”
Holds: README, license file, environment (environment.yml, requirements.txt), 29 notebooks
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: NumPy (63 files), scikit-learn (37 files), SciPy (37 files), Matplotlib (33 files), seaborn (28 files), pandas (27 files), Plotly (25 files), statsmodels (22 files), h5py (18 files), PyTorch (15 files), PyTorch Lightning (9 files), Keras (1 file), TensorFlow (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
76 files
At the source: github.com/coganlab/cross_patient_speech_decoding

Zenodo 20531684

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: the references
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (63 files), scikit-learn (37 files), SciPy (37 files), Matplotlib (33 files), seaborn (28 files), pandas (27 files), Plotly (25 files), statsmodels (22 files), h5py (18 files), PyTorch (15 files), PyTorch Lightning (9 files), Keras (1 file), TensorFlow (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)
  • 27 September 2026: the link answers (HTTP 200)
76 files
At the source:

Code availability statement

The paper has a code availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41467-026-75455-1.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 3 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 177 scripts, each with its path and the digest of its content;
  • 23 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data availability statement

The paper has a data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

  • no repository, dataset or request procedure was recognized in it

Read it in the paper: doi.org/10.1038/s41467-026-75455-1.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 11 authors, 3 keywords, 8 MeSH terms, 3 funders, 52 references.

Cite

This paper

Spalding, Z., Duraivel, S., Rahimpour, S., Wang, C., Barth, K., Schmitz, C., Lad, S. P., Friedman, A. H., Southwell, D. G., Viventi, J., & Cogan, G. B. (2026). Shared latent representations of speech production for cross-patient speech decoding. Nature communications, 17(1), 8716. https://doi.org/10.1038/s41467-026-75455-1

BibTeX

@article{spalding2026shared,
author = {Spalding, Z. and Duraivel, S. and Rahimpour, S. and Wang, C. and Barth, K. and Schmitz, C. and Lad, S. P. and Friedman, A. H. and Southwell, D. G. and Viventi, J. and Cogan, G. B.},
title = {{Shared latent representations of speech production for cross-patient speech decoding}},
journal = {Nature communications},
year = {2026},
month = jul,
volume = {17},
number = {1},
pages = {8716},
publisher = {Nature Publishing Group},
issn = {2041-1723},
doi = {10.1038/s41467-026-75455-1},
url = {https://doi.org/10.1038/s41467-026-75455-1},
pmid = {42463660},
pmcid = {PMC13490415}
}

RIS

TY - JOUR
AU - Spalding, Z.
AU - Duraivel, S.
AU - Rahimpour, S.
AU - Wang, C.
AU - Barth, K.
AU - Schmitz, C.
AU - Lad, S. P.
AU - Friedman, A. H.
AU - Southwell, D. G.
AU - Viventi, J.
AU - Cogan, G. B.
TI - Shared latent representations of speech production for cross-patient speech decoding
T2 - Nature communications
J2 - Nat Commun
PY - 2026
DA - 2026/07/16
VL - 17
IS - 1
SP - 8716
SN - 2041-1723
PB - Nature Publishing Group
DO - 10.1038/s41467-026-75455-1
UR - https://doi.org/10.1038/s41467-026-75455-1
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41467-026-75455-1",
"type": "article-journal",
"title": "Shared latent representations of speech production for cross-patient speech decoding",
"container-title": "Nature communications",
"author": [
{
"family": "Spalding",
"given": "Z."
},
{
"family": "Duraivel",
"given": "S."
},
{
"family": "Rahimpour",
"given": "S."
},
{
"family": "Wang",
"given": "C."
},
{
"family": "Barth",
"given": "K."
},
{
"family": "Schmitz",
"given": "C."
},
{
"family": "Lad",
"given": "S. P."
},
{
"family": "Friedman",
"given": "A. H."
},
{
"family": "Southwell",
"given": "D. G."
},
{
"family": "Viventi",
"given": "J."
},
{
"family": "Cogan",
"given": "G. B."
}
],
"container-title-short": "Nat Commun",
"volume": "17",
"issue": "1",
"page": "8716",
"DOI": "10.1038/s41467-026-75455-1",
"PMID": "42463660",
"PMCID": "PMC13490415",
"ISSN": "2041-1723",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41467-026-75455-1",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
16
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41467-026-71284-4 [code]
Encoding of speech modes and loudness in ventral precentral gyrus.
Journal: Nature communications
In common: seaborn, scikit-learn, pandas, 3 other tools, cognitive, 7 references
[2] doi:10.1038/s41586-026-10691-5 [code]
Mapping the neuronal building blocks of human language with language models.
Journal: Nature
In common: statsmodels, scikit-learn, pandas, 3 other tools, cognitive, 7 references
[3] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: PyTorch Lightning, Keras, TensorFlow, 10 other tools
[4] doi:10.1523/eneuro.0023-26.2026 [code]
Real-Time Segmentation and Classification of Birdsong Syllables for Learning Experiments.
Journal: eNeuro
In common: PyTorch Lightning, Keras, TensorFlow, 8 other tools, cognitive
[5] doi:10.1073/pnas.2536563123 [code]
Temporally structured motor and auditory representations in covert syllable production.
Journal: Proceedings of the National Academy of Sciences of the United States of America
In common: statsmodels, scikit-learn, pandas, 3 other tools, cognitive, 5 references
[6] doi:10.1038/s41562-026-02414-7 [code]
Optimized feature gains explain and predict successes and failures of human selective listening.
Journal: Nature human behaviour
In common: PyTorch Lightning, TensorFlow, h5py, 8 other tools, cognitive
[7] doi:10.7554/elife.109400 [code]
High-fidelity neural speech reconstruction through an efficient acoustic-linguistic dual-pathway framework.
Journal: eLife
In common: PyTorch Lightning, PyTorch, SciPy, 2 other tools, intracranial EEG (iEEG / ECoG / SEEG), cognitive, 4 references
[8] doi:10.1038/s41586-026-10331-y [code]
Active dissociation of intracortical spiking and high gamma activity.
Journal: Nature
In common: TensorFlow, h5py, scikit-learn, 4 other tools, 4 references
[9] doi:10.1038/s42003-026-10169-0 [code]
Shared representations in brains and models reveal a two-route cortical organization during scene perception.
Journal: Communications biology
In common: Plotly, h5py, statsmodels, 7 other tools, cognitive, 2 references
[10] doi:10.1038/s41597-025-05174-7 [code]
A large-scale MEG and EEG dataset for object recognition in naturalistic scenes
Journal: n/a
In common: Keras, TensorFlow, Plotly, 8 other tools

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.