Pengfei Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pengfei Sun has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Edward F. Chang
Department of Neurological Surgery, University of California, San Francisco, San Francisco, USA
2 shared publications - Jun Qin
Southern Illinois University
2 shared publications Adelyn Tu-Chan
From the Department of Neurological Surgery (D.A.M., S.L.M., J.R.L., G.K.A., J.G.M., P.F.S., J.C., M.E.D., E.F.C.), the Weill Institute for Neuroscience (D.A.M., S.L.M., J.R.L., G.K.A., J.G.M., P.F.S., J.C., K.G., E.F.C.), and the Departments of Rehabilitation Services (P.M.L.) and Neurology (G.M.A., A.T.-C., K.G.), University of California, San Francisco (UCSF), San Francisco, and the Graduate Program in Bioengineering, University of California, Berkeley–UCSF, Berkeley (S.L.M., J.R.L., E.F.C.).
1 shared publicationAli Mahdi
Southern Illinois Univ, Dept Elect & Comp Engn, Carbondale, IL 62901 USA
1 shared publication- David Aaron Moses
Department of Neurological Surgery, University of California, San Francisco, San Francisco, USA
1 shared publication Gary M. Abrams
From the Department of Neurological Surgery (D.A.M., S.L.M., J.R.L., G.K.A., J.G.M., P.F.S., J.C., M.E.D., E.F.C.), the Weill Institute for Neuroscience (D.A.M., S.L.M., J.R.L., G.K.A., J.G.M., P.F.S., J.C., K.G., E.F.C.), and the Departments of Rehabilitation Services (P.M.L.) and Neurology (G.M.A., A.T.-C., K.G.), University of California, San Francisco (UCSF), San Francisco, and the Graduate Program in Bioengineering, University of California, Berkeley–UCSF, Berkeley (S.L.M., J.R.L., E.F.C.).
1 shared publication
Latest Publications
- Top Cited Papers
- 15 July 2021
- Published by Massachusetts Medical Society in New England Journal of Medicine
- Vol. 385 (3) , 217-227
Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria
Technology to restore the ability to communicate in paralyzed persons who cannot speak has the potential to improve autonomy and quality of life. An approach that decodes words and sentences directly from the cerebral cortical activity of such patients may represent an advancement over existing methods for assisted communication. We implanted a subdural, high-density, multielectrode array over the area of the sensorimotor cortex that controls speech in a person with anarthria (the loss of the ability to articulate speech) and spastic quadriparesis caused by a brain-stem stroke. Over the course of 48 sessions, we recorded 22 hours of cortical activity while the participant attempted to say individual words from a vocabulary set of 50 words. We used deep-learning algorithms to create computational models for the detection and classification of words from patterns in the recorded cortical activity. We applied these computational models, as well as a natural-language model that yielded next-word probabilities given the preceding words in a sequence, to decode full sentences as the participant attempted to say them. We decoded sentences from the participant’s cortical activity in real time at a median rate of 15.2 words per minute, with a median word error rate of 25.6%. In post hoc analyses, we detected 98% of the attempts by the participant to produce individual words, and we classified words with 47.1% accuracy using cortical signals that were stable throughout the 81-week study period. In a person with anarthria and spastic quadriparesis caused by a brain-stem stroke, words and sentences were decoded directly from cortical activity during attempted speech with the use of deep-learning models and a natural-language model. (Funded by Facebook and others; ClinicalTrials.gov number, NCT03698149.)
- 15 July 2021
- Published by Massachusetts Medical Society in New England Journal of Medicine
- Vol. 385 (3) , 217-227
Top Cited PapersNeuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria
Technology to restore the ability to communicate in paralyzed persons who cannot speak has the potential to improve autonomy and quality of life. An approach that decodes words and sentences directly from the cerebral cortical activity of such patients may represent an advancement over existing methods for assisted communication. We implanted a subdural, high-density, multielectrode array over the area of the sensorimotor cortex that controls speech in a person with anarthria (the loss of the ability to articulate speech) and spastic quadriparesis caused by a brain-stem stroke. Over the course of 48 sessions, we recorded 22 hours of cortical activity while the participant attempted to say individual words from a vocabulary set of 50 words. We used deep-learning algorithms to create computational models for the detection and classification of words from patterns in the recorded cortical activity. We applied these computational models, as well as a natural-language model that yielded next-word probabilities given the preceding words in a sequence, to decode full sentences as the participant attempted to say them. We decoded sentences from the participant’s cortical activity in real time at a median rate of 15.2 words per minute, with a median word error rate of 25.6%. In post hoc analyses, we detected 98% of the attempts by the participant to produce individual words, and we classified words with 47.1% accuracy using cortical signals that were stable throughout the 81-week study period. In a person with anarthria and spastic quadriparesis caused by a brain-stem stroke, words and sentences were decoded directly from cortical activity during attempted speech with the use of deep-learning models and a natural-language model. (Funded by Facebook and others; ClinicalTrials.gov number, NCT03698149.)
- 16 December 2020
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 17 (6) , 066015
Brain2Char: a deep architecture for decoding text from brain recordings
Objective. Decoding language representations directly from the brain can enable new brain–computer interfaces (BCIs) for high bandwidth human–human and human–machine communication. Clinically, such technologies can restore communication in people with neurological conditions affecting their ability to speak. Approach . In this study, we propose a novel deep network architecture Brain2Char, for directly decoding text (specifically character sequences) from direct brain recordings (called electrocorticography, ECoG). Brain2Char framework combines state-of-the-art deep learning modules—3D Inception layers for multiband spatiotemporal feature extraction from neural data and bidirectional recurrent layers, dilated convolution layers followed by language model weighted beam search to decode character sequences, and optimizing a connectionist temporal classification loss. Additionally, given the highly non-linear transformations that underlie the conversion of cortical function to character sequences, we perform regularizations on the network’s latent representations motivated by insights into cortical encoding of speech production and artifactual aspects specific to ECoG data acquisition. To do this, we impose auxiliary losses on latent representations for articulatory movements, speech acoustics and session specific non-linearities. Main results. In three (out of four) participants reported here, Brain2Char achieves 10.6%, 8.5%, and 7.0% word error rates respectively on vocabulary sizes ranging from 1200 to 1900 words. Significance. These results establish a new end-to-end approach on decoding text from brain signals and demonstrate the potential of Brain2Char as a high-performance communication BCI.
- 16 December 2020
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 17 (6) , 066015
Brain2Char: a deep architecture for decoding text from brain recordings
Objective. Decoding language representations directly from the brain can enable new brain–computer interfaces (BCIs) for high bandwidth human–human and human–machine communication. Clinically, such technologies can restore communication in people with neurological conditions affecting their ability to speak. Approach . In this study, we propose a novel deep network architecture Brain2Char, for directly decoding text (specifically character sequences) from direct brain recordings (called electrocorticography, ECoG). Brain2Char framework combines state-of-the-art deep learning modules—3D Inception layers for multiband spatiotemporal feature extraction from neural data and bidirectional recurrent layers, dilated convolution layers followed by language model weighted beam search to decode character sequences, and optimizing a connectionist temporal classification loss. Additionally, given the highly non-linear transformations that underlie the conversion of cortical function to character sequences, we perform regularizations on the network’s latent representations motivated by insights into cortical encoding of speech production and artifactual aspects specific to ECoG data acquisition. To do this, we impose auxiliary losses on latent representations for articulatory movements, speech acoustics and session specific non-linearities. Main results. In three (out of four) participants reported here, Brain2Char achieves 10.6%, 8.5%, and 7.0% word error rates respectively on vocabulary sizes ranging from 1200 to 1900 words. Significance. These results establish a new end-to-end approach on decoding text from brain signals and demonstrate the potential of Brain2Char as a high-performance communication BCI.
- 1 July 2018
- Published by Elsevier in Speech Communication
- Vol. 101, 57-69
Speech enhancement in spectral envelope and details subspaces
- 1 July 2018
- Published by Elsevier in Speech Communication
- Vol. 101, 57-69
Speech enhancement in spectral envelope and details subspaces
- Open Access
- 1 February 2017
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 141 (2) , 808-817
Speech enhancement via two-stage dual tree complex wavelet packet transform with a speech presence probability estimator
In this paper, a two-stage dual tree complex wavelet packet transform (DTCWPT) based speech enhancement algorithm has been proposed, in which a speech presence probability (SPP) estimator and a generalized minimum mean squared error (MMSE) estimator are developed. To overcome the drawback of signal distortions caused by down sampling of wavelet packet transform (WPT), a two-stage analytic decomposition concatenating undecimated wavelet packet transform (UWPT) and decimated WPT is employed. An SPP estimator in the DTCWPT domain is derived based on a generalized Gamma distribution of speech, and Gaussian noise assumption. The validation results show that the proposed algorithm can obtain enhanced perceptual evaluation of speech quality (PESQ), and segmental signal-to-noise ratio (SegSNR) at low signal-to-noise ratio (SNR) nonstationary noise, compared with four other state-of-the-art speech enhancement algorithms, including optimally modified log-spectral amplitude (OM-LSA), soft masking using a posteriori SNR uncertainty (SMPO), a posteriori SPP based MMSE estimation (MMSE-SPP), and adaptive Bayesian wavelet thresholding (BWT).
- 1 February 2017
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 141 (2) , 808-817
Open AccessSpeech enhancement via two-stage dual tree complex wavelet packet transform with a speech presence probability estimator
In this paper, a two-stage dual tree complex wavelet packet transform (DTCWPT) based speech enhancement algorithm has been proposed, in which a speech presence probability (SPP) estimator and a generalized minimum mean squared error (MMSE) estimator are developed. To overcome the drawback of signal distortions caused by down sampling of wavelet packet transform (WPT), a two-stage analytic decomposition concatenating undecimated wavelet packet transform (UWPT) and decimated WPT is employed. An SPP estimator in the DTCWPT domain is derived based on a generalized Gamma distribution of speech, and Gaussian noise assumption. The validation results show that the proposed algorithm can obtain enhanced perceptual evaluation of speech quality (PESQ), and segmental signal-to-noise ratio (SegSNR) at low signal-to-noise ratio (SNR) nonstationary noise, compared with four other state-of-the-art speech enhancement algorithms, including optimally modified log-spectral amplitude (OM-LSA), soft masking using a posteriori SNR uncertainty (SMPO), a posteriori SPP based MMSE estimation (MMSE-SPP), and adaptive Bayesian wavelet thresholding (BWT).