{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T00:09:59Z","timestamp":1769299799445,"version":"3.49.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1016\/j.knosys.2023.110837","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T12:39:17Z","timestamp":1690288757000},"page":"110837","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":13,"special_numbering":"C","title":["End-to-end translation of human neural activity to speech with a dual\u2013dual generative adversarial network"],"prefix":"10.1016","volume":"277","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0998-2448","authenticated-orcid":false,"given":"Yina","family":"Guo","sequence":"first","affiliation":[]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Anhong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2023.110837_b1","first-page":"1","article-title":"Decoding visual neural representations by multimodal learning of brain-visual-linguistic features","author":"Du","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2023.110837_b2","doi-asserted-by":"crossref","unstructured":"P. Singh, P. Pandey, K. Miyapuram, S. Raman, EEG2IMAGE: Image Reconstruction from EEG Brain Signals, in: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2023, pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10096587"},{"key":"10.1016\/j.knosys.2023.110837_b3","doi-asserted-by":"crossref","first-page":"130","DOI":"10.3389\/fncom.2016.00130","article-title":"Multimodal neural network for rapid serial visual presentation brain computer interface","volume":"10","author":"Manor","year":"2016","journal-title":"Front. Comput. Neurosci."},{"issue":"3","key":"10.1016\/j.knosys.2023.110837_b4","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/aa6213","article-title":"An improved P300 pattern in BCI to catch user\u2019s attention","volume":"14","author":"Jin","year":"2017","journal-title":"J. Neural Eng."},{"issue":"4","key":"10.1016\/j.knosys.2023.110837_b5","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1111\/psyp.12807","article-title":"The elicitation of steady-state visual evoked potentials during sleep","volume":"54","author":"Norton","year":"2017","journal-title":"Psychophysiology"},{"key":"10.1016\/j.knosys.2023.110837_b6","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3389\/fncom.2019.00024","article-title":"Investigation of visual stimulus with various colors and the layout for the oddball paradigm in evoked related potential-based brain\u2013computer interface","volume":"13","author":"Guo","year":"2019","journal-title":"Front. Comput. Neurosci."},{"issue":"24","key":"10.1016\/j.knosys.2023.110837_b7","doi-asserted-by":"crossref","first-page":"7198","DOI":"10.3390\/s20247198","article-title":"Single-option P300-BCI performance is affected by visual stimulation conditions","volume":"20","author":"Chailloux\u00a0Peguero","year":"2020","journal-title":"Sensors-Basel"},{"key":"10.1016\/j.knosys.2023.110837_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2021.102542","article-title":"Transfer learning and SpecAugment applied to SSVEP based BCI classification","volume":"67","author":"Bassi","year":"2021","journal-title":"Biomed. Signal Process."},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b9","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.jneumeth.2007.02.009","article-title":"An auditory brain\u2013computer interface (BCI)","volume":"167","author":"Nijboer","year":"2008","journal-title":"J. Neurosci. Methods"},{"issue":"7","key":"10.1016\/j.knosys.2023.110837_b10","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1016\/j.clinph.2009.04.019","article-title":"Toward a high-throughput auditory P300-based brain\u2013computer interface","volume":"120","author":"Klobassa","year":"2009","journal-title":"Clin. Neurophysiol."},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b11","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1111\/j.1749-6632.2008.04122.x","article-title":"A brain\u2013computer interface controlled auditory event-related potential (P300) spelling system for locked-in patients","volume":"1157","author":"K\u00fcbler","year":"2009","journal-title":"Ann. NY Acad. Sci."},{"key":"10.1016\/j.knosys.2023.110837_b12","doi-asserted-by":"crossref","unstructured":"K.-W. Lee, D.-H. Lee, S.-J. Kim, S.-W. Lee, Decoding Neural Correlation of Language-Specific Imagined Speech using EEG Signals, in: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, EMBC, 2022, pp. 1977\u20131980.","DOI":"10.1109\/EMBC48229.2022.9871721"},{"key":"10.1016\/j.knosys.2023.110837_b13","first-page":"99","article-title":"A novel 9-class auditory ERP paradigm driving a predictive text entry system","volume":"5","author":"H\u00f6hne","year":"2011","journal-title":"Front. Neurosci-Switz."},{"issue":"4","key":"10.1016\/j.knosys.2023.110837_b14","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2560\/9\/4\/045003","article-title":"Natural stimuli improve auditory BCIs with respect to ergonomics and performance","volume":"9","author":"H\u00f6hne","year":"2012","journal-title":"J. Neural Eng."},{"issue":"11","key":"10.1016\/j.knosys.2023.110837_b15","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1005119","article-title":"Real-time control of an articulatory-based speech synthesizer for brain computer interfaces","volume":"12","author":"Bocquelet","year":"2016","journal-title":"PLoS Comput. Biol."},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b16","first-page":"1","article-title":"Towards reconstructing intelligible speech from the human auditory cortex","volume":"9","author":"Akbari","year":"2019","journal-title":"Sci. Rep-UK"},{"issue":"7753","key":"10.1016\/j.knosys.2023.110837_b17","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","article-title":"Speech synthesis from neural decoding of spoken sentences","volume":"568","author":"Anumanchipalli","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2023.110837_b18","doi-asserted-by":"crossref","unstructured":"Z. Wang, H. Ji, Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification, in: AAAI Conference on Artificial Intelligence, vol. 36, 2021, pp. 5350\u20135358.","DOI":"10.1609\/aaai.v36i5.20472"},{"issue":"4","key":"10.1016\/j.knosys.2023.110837_b19","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/s41593-020-0608-8","article-title":"Machine translation of cortical activity to text with an encoder\u2013decoder framework","volume":"23","author":"Makin","year":"2020","journal-title":"Nature Neurosci."},{"key":"10.1016\/j.knosys.2023.110837_b20","article-title":"High-performance brain-to-text communication via imagined handwriting","author":"Willett","year":"2020","journal-title":"BioRxiv"},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b21","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.jneumeth.2011.02.007","article-title":"Classification of selective attention to auditory stimuli: Toward vision-free brain\u2013computer interfacing","volume":"197","author":"Kim","year":"2011","journal-title":"J. Neurosci. Methods"},{"key":"10.1016\/j.knosys.2023.110837_b22","series-title":"International Evoked Response Audiometry Study Group (IERASG), Date: 2013\/06\/10-2013\/06\/13, Location: New Orleans, Louisiana, USA","article-title":"Lateralization of auditory steady-state responses to speech envelope modulations","author":"De\u00a0Vos","year":"2013"},{"key":"10.1016\/j.knosys.2023.110837_b23","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.neubiorev.2014.02.009","article-title":"From sensation to percept: the neural signature of auditory event-related potentials","volume":"42","author":"Joos","year":"2014","journal-title":"Neurosci. Biobehav. R."},{"issue":"2","key":"10.1016\/j.knosys.2023.110837_b24","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1016\/j.clinph.2015.08.007","article-title":"Training leads to increased auditory brain\u2013computer interface performance of end-users with motor impairments","volume":"127","author":"Halder","year":"2016","journal-title":"Clin. Neurophysiol."},{"key":"10.1016\/j.knosys.2023.110837_b25","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.compbiomed.2017.03.011","article-title":"Music and natural sounds in an auditory steady-state response based brain\u2013computer interface to increase user acceptance","volume":"84","author":"Heo","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.knosys.2023.110837_b26","doi-asserted-by":"crossref","first-page":"391","DOI":"10.3389\/fnhum.2018.00391","article-title":"Eyes-closed increases the usability of brain-computer interfaces based on auditory event-related potentials","volume":"12","author":"H\u00fcbner","year":"2018","journal-title":"Front. Hum. Neurosci."},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b27","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/s11571-017-9456-y","article-title":"Usage of drip drops as stimuli in an auditory P300 BCI paradigm","volume":"12","author":"Huang","year":"2018","journal-title":"Cogn. Neurodyn."},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37359-z","article-title":"Towards reconstructing intelligible speech from the human auditory cortex","volume":"9","author":"Akbari","year":"2019","journal-title":"Sci. Rep."},{"key":"10.1016\/j.knosys.2023.110837_b29","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","article-title":"Speech synthesis from neural decoding of spoken sentences","volume":"568","author":"Anumanchipalli","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2023.110837_b30","series-title":"Decoding speech from non-invasive brain recordings","author":"D\u00e9fossez","year":"2022"},{"key":"10.1016\/j.knosys.2023.110837_b31","doi-asserted-by":"crossref","first-page":"2140","DOI":"10.1109\/TNSRE.2023.3268751","article-title":"Speech2EEG: Leveraging pretrained speech model for EEG signal recognition","volume":"31","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"10.1016\/j.knosys.2023.110837_b32","doi-asserted-by":"crossref","unstructured":"F. Cui, L. Guo, L. He, J. Liu, E. Pei, Y. Wang, D. Jiang, Relate Auditory Speech To Eeg By Shallow-Deep Attention-Based Network, in: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2023, pp. 1\u20132.","DOI":"10.1109\/ICASSP49357.2023.10094934"},{"key":"10.1016\/j.knosys.2023.110837_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2019.116211","article-title":"Stimulus-aware spatial filtering for single-trial neural response and temporal response function estimation in high-density EEG with applications in auditory research","volume":"204","author":"Das","year":"2020","journal-title":"Neuroimage"},{"key":"10.1016\/j.knosys.2023.110837_b34","series-title":"2020 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1235","article-title":"Speech synthesis using EEG","author":"Krishna","year":"2020"},{"issue":"2","key":"10.1016\/j.knosys.2023.110837_b35","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/abdd44","article-title":"Speech stream segregation to control an ERP-based auditory BCI","volume":"18","author":"Velasco-\u00c1lvarez","year":"2021","journal-title":"J. Neural Eng."},{"key":"10.1016\/j.knosys.2023.110837_b36","series-title":"Autoencoders","author":"Bank","year":"2020"},{"issue":"1","key":"10.1016\/j.knosys.2023.110837_b37","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1166\/jctn.2020.8648","article-title":"An overview of deep learning architecture of deep neural networks and autoencoders","volume":"17","author":"Sewak","year":"2020","journal-title":"J. Comput. Theor. Nanosci."},{"key":"10.1016\/j.knosys.2023.110837_b38","doi-asserted-by":"crossref","unstructured":"Z. Yi, H. Zhang, P. Tan, M. Gong, DualGAN: Unsupervised dual learning for image-to-image translation, in: Proceedings of the IEEE International Conference on Computer Vision, ICCV, 2017, pp. 2849\u20132857.","DOI":"10.1109\/ICCV.2017.310"},{"key":"10.1016\/j.knosys.2023.110837_b39","doi-asserted-by":"crossref","unstructured":"J. Zhu, T. Park, P. Isola, A.A. Efros, Unpaired image-to-image translation using cycle-consistent adversarial networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"10.1016\/j.knosys.2023.110837_b40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2023.110837_b41","first-page":"217","article-title":"Brain-to-text: decoding spoken phrases from phone representations in the brain","volume":"9","author":"Herff","year":"2015","journal-title":"Front. Neurosci-Switz."},{"key":"10.1016\/j.knosys.2023.110837_b42","doi-asserted-by":"crossref","unstructured":"J.S. Brumberg, P.R. Kennedy, F.H. Guenther, Artificial speech synthesizer control by brain-computer interface, in: Proceedings of the Annual Conference of the International Speech Communication Association, 2009, pp. 636\u2013639.","DOI":"10.21437\/Interspeech.2009-225"},{"key":"10.1016\/j.knosys.2023.110837_b43","first-page":"2672","article-title":"Generative adversarial networks","volume":"3","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inform. Proces. Syst."},{"issue":"8","key":"10.1016\/j.knosys.2023.110837_b44","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1109\/TCSVT.2018.2867934","article-title":"Generating realistic videos from keyframes with concatenated GANs","volume":"29","author":"Wen","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2023.110837_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109595","article-title":"Synchronization of multiple reaction\u2013diffusion memristive neural networks with known or unknown parameters and switching topologies","volume":"254","author":"Cao","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.110837_b46","series-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","first-page":"3","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"10.1016\/j.knosys.2023.110837_b47","series-title":"European Conference on Computer Vision, ECCV","first-page":"702","article-title":"Precomputed real-time texture synthesis with markovian generative adversarial networks","author":"Li","year":"2016"},{"issue":"3","key":"10.1016\/j.knosys.2023.110837_b48","first-page":"397","article-title":"Accuracy assessment: a user\u2019s perspective","volume":"52","author":"Story","year":"1986","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"10.1016\/j.knosys.2023.110837_b49","series-title":"Noise Reduction in Speech Processing","first-page":"1","article-title":"Pearson correlation coefficient","author":"Benesty","year":"2009"},{"key":"10.1016\/j.knosys.2023.110837_b50","doi-asserted-by":"crossref","unstructured":"R. Kubichek, Mel-cepstral distance measure for objective speech quality assessment, in: Proceedings of IEEE Pacific Rim Conference on Communications Computers and Signal Processing, vol. 1, 1993, pp. 125\u2013128, http:\/\/dx.doi.org\/10.1109\/PACRIM.1993.407206.","DOI":"10.1109\/PACRIM.1993.407206"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705123005877?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705123005877?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:02:26Z","timestamp":1760594546000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705123005877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":50,"alternative-id":["S0950705123005877"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2023.110837","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2023,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"End-to-end translation of human neural activity to speech with a dual\u2013dual generative adversarial network","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2023.110837","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"110837"}}