Sleep deprivation changes frequency-specific functional organization of the resting human brain.

Previous resting-state functional magnetic resonance imaging (rs-fMRI) studies have widely explored the temporal connection changes in the human brain following long-term sleep deprivation (SD). However, the frequency-specific topological properties of sleep-deprived functional networks remain virtually unclear. In this study, thirty-seven healthy male subjects underwent resting-state fMRI during rested wakefulness (RW) and after 36 hours of SD, and we examined frequency-specific spectral connection changes (0.01-0.08 Hz, interval = 0.01 Hz) caused by SD. First, we conducted a multivariate pattern analysis combining linear SVM classifiers with a robust feature selection algorithm, and the results revealed that accuracies of 74.29%-84.29% could be achieved in the classification between RW and SD states in leave-one-out cross-validation at different frequency bands, moreover, the spectral connection at the lowest and highest frequency bands exhibited higher discriminative power. Connection involving the cingulo-opercular network increased most, while connection involving the default-mode network decreased most following SD. Then we performed a graph-theoretic analysis and observed reduced low-frequency modularity and high-frequency global efficiency in the SD state. Moreover, hub regions, which were primarily situated in the cerebellum and the cingulo-opercular network after SD, exhibited high discriminative power in the aforementioned classification consistently. The findings may indicate the frequency-dependent effects of SD on the functional network topology and its efficiency of information exchange, providing new insights into the impact of SD on the human brain.

Frequency-specific segregation and integration of human cerebral cortex: An intrinsic functional atlas.

The cognitive and behavioral functions of the human brain are supported by its frequency multiplexing mechanism. However, there is limited understanding of the dynamics of the functional network topology. This study aims to investigate the frequency-specific topology of the functional human brain using 7T rs-fMRI data. Frequency-specific parcellations were first performed, revealing frequency-dependent dynamics within the frontoparietal control, parietal memory, and visual networks. An intrinsic functional atlas containing 456 parcels was proposed and validated using stereo-EEG. Graph theory analysis suggested that, in addition to the task-positive vs. task-negative organization observed in static networks, there was a cognitive control system additionally from a frequency perspective. The reproducibility and plausibility of the identified hub sets were confirmed through 3T fMRI analysis, and their artificial removal had distinct effects on network topology. These results indicate a more intricate and subtle dynamics of the functional human brain and emphasize the significance of accurate topography.

SWCNTs/PEDOT:PSS nanocomposites-modified microelectrode arrays for revealing locking relations between burst and local field potential in cultured cortical networks.

Burst and local field potential (LFP) are fundamental components of brain activity, representing fast and slow rhythms, respectively. Understanding the intricate relationship between burst and LFP is crucial for deciphering the underlying mechanisms of brain dynamics. In this study, we fabricated high-performance microelectrode arrays (MEAs) using the SWCNTs/PEDOT:PSS nanocomposites, which exhibited favorable electrical properties (low impedance: 12.8 ± 2.44 kΩ) and minimal phase delay (-11.96 ± 1.64°). These MEAs enabled precise exploration of the burst-LFP interaction in cultured cortical networks. After a 14-day period of culture, we used the MEAs to monitor electrophysiological activities and revealed a time-locking relationship between burst and LFP, indicating the maturation of the neural network. To further investigate this relationship, we modulated burst firing patterns by treating the neural culture with increasing concentrations of glycine. The results indicated that glycine effectively altered burst firing patterns, with both duration and spike count increasing as the concentration rose. This was accompanied by an enhanced level of time-locking between burst and LFP but a decrease in synchrony among neurons. This study not only highlighted the pivotal role of SWCNTs/PEDOT:PSS-modified MEAs in elucidating the interaction between burst and LFP, bridging the gap between slow and fast brain rhythms in vitro but also provides valuable insights into the potential therapeutic strategies targeting neurological disorders associated with abnormal rhythm generation.

Effect of Phase Clustering Bias on Phase-Amplitude Coupling for Emotional EEG.

BACKGROUND: Emotions are thought to be related to distinct patterns of neural oscillations, but the interactions among multi-frequency neural oscillations during different emotional states lack full exploration. Phase-amplitude coupling is a promising tool for understanding the complexity of the neurophysiological system, thereby playing a crucial role in revealing the physiological mechanisms underlying emotional electroencephalogram (EEG). However, the non-sinusoidal characteristics of EEG lead to the non-uniform distribution of phase angles, which could potentially affect the analysis of phase-amplitude coupling. Removing phase clustering bias (PCB) can uniform the distribution of phase angles, but the effect of this approach is unknown on emotional EEG phase-amplitude coupling. This study aims to explore the effect of PCB on cross-frequency phase-amplitude coupling for emotional EEG. METHODS: The technique of removing PCB was implemented on a publicly accessible emotional EEG dataset to calculate debiased phase-amplitude coupling. Statistical analysis and classification were conducted to compare the difference in emotional EEG phase-amplitude coupling prior to and post the removal of PCB. RESULTS: Emotional EEG phase-amplitude coupling values are overestimated due to PCB. Removing PCB enhances the difference in coupling strength between fear and happy emotions in the frontal lobe. Comparable emotion recognition performance was achieved with fewer features after removing PCB. CONCLUSIONS: These findings suggest that removing PCB enhances the difference in emotional EEG phase-amplitude coupling patterns and generates features that contain more emotional information. Removing PCB may be advantageous for analyzing emotional EEG phase-amplitude coupling and recognizing human emotions.

Fusion of Multi-domain EEG Signatures Improves Emotion Recognition.

BACKGROUND: Affective computing has gained increasing attention in the area of the human-computer interface where electroencephalography (EEG)-based emotion recognition occupies an important position. Nevertheless, the diversity of emotions and the complexity of EEG signals result in unexplored relationships between emotion and multichannel EEG signal frequency, as well as spatial and temporal information. METHODS: Audio-video stimulus materials were used that elicited four types of emotions (sad, fearful, happy, neutral) in 32 male and female subjects (age 21-42 years) while collecting EEG signals. We developed a multidimensional analysis framework using a fusion of phase-locking value (PLV), microstates, and power spectral densities (PSDs) of EEG features to improve emotion recognition. RESULTS: An increasing trend of PSDs was observed as emotional valence increased, and connections in the prefrontal, temporal, and occipital lobes in high-frequency bands showed more differentiation between emotions. Transition probability between microstates was likely related to emotional valence. The average cross-subject classification accuracy of features fused by Discriminant Correlation Analysis achieved 64.69%, higher than that of single mode and direct-concatenated features, with an increase of more than 7%. CONCLUSIONS: Different types of EEG features have complementary properties in emotion recognition, and combining EEG data from three types of features in a correlated way, improves the performance of emotion classification.

Multimodal Vigilance Estimation With Modality-Pairwise Contrastive Loss.

Nowadays, how to estimate vigilance with higher accuracy has become a hot field of research direction. Although the increasing available modalities opens the door for amazing new possibilities to achieve good performance, the uncertain cross-modal interaction still poses a real challenge to the multimodal fusion. In this paper, a cross-modality alignment method has been proposed based on the contrastive learning for extracting shared but not the same information among modalities. The contrastive learning is adopted to minimize the intermodal differences by maximizing the similarity of semantic representation of modalities. Applying our proposed modeling framework, we evaluated our approach on SEED-VIG dataset consisting of EEG and EOG signals. Experiments showed that our study achieved state-of-the-art multimodal vigilance estimation performance both in intra-subject and inter-subject situations, the average of RMSE/CORR were improved to 0.092/0.893 and 0.144/0.887, respectively. In addition, analysis on the frequency bands showed that theta and alpha activities contain valuable information for vigilance estimation, and the correlation between them and PERCLOS can be significantly improved by contrastive learning. We argue that the proposed method in the inter-subject case could offer the possibility of reducing the high-cost of data annotation, and further analysis may provide an idea for the application of multimodal vigilance regression.

Spontaneous alpha-band oscillations reflect individual differences in audiovisual temporal perception.

Light, and sound are persistently out of sync for subjective temporal perception called point of subjective simultaneity (PSS). It is stable within individuals but variable among individuals. Previous studies found that spontaneous alpha power, functioning in attention-related brain states, predicts individual PSS in the temporal order judgment (TOJ) task. However, the neural mechanisms underlying individual differences in audiovisual PSS have not been elucidated in the simultaneity judgment (SJ) task. A hypothesis that the spontaneous alpha band power might reflect the individual subjective temporal bias was proposed. We designed an SJ task EEG experiment where subjects judged whether the beep-flash stimuli are synchronous to test the above hypothesis. We primarily explored the correlation between the alpha-band power differences (visual- and auditory-leading conditions) with individual PSS. We used the V50A (~50% proportion of synchronous responses) to represent visual-leading conditions while A50V represents auditory-leading ones. We found the higher alpha power difference (V50A - A50V) predicted larger individual PSS. This study extends previous results and found that individual difference effects in the alpha band power also exist in the SJ task. The results suggested that alpha power might be associated with a spontaneous attentional state and reflect individuals' subjective temporal bias.

The increasing instance of negative emotion reduce the performance of emotion recognition.

Introduction: Emotion recognition plays a crucial role in affective computing. Recent studies have demonstrated that the fuzzy boundaries among negative emotions make recognition difficult. However, to the best of our knowledge, no formal study has been conducted thus far to explore the effects of increased negative emotion categories on emotion recognition. Methods: A dataset of three sessions containing consistent non-negative emotions and increased types of negative emotions was designed and built which consisted the electroencephalogram (EEG) and the electrocardiogram (ECG) recording of 45 participants. Results: The results revealed that as negative emotion categories increased, the recognition rates decreased by more than 9%. Further analysis depicted that the discriminative features gradually reduced with an increase in the negative emotion types, particularly in the θ, α, and ß frequency bands. Discussion: This study provided new insight into the balance of emotion-inducing stimuli materials.

An Improved Canonical Correlation Analysis for EEG Inter-Band Correlation Extraction.

(1) Background: Emotion recognition based on EEG signals is a rapidly growing and promising research field in affective computing. However, traditional methods have focused on single-channel features that reflect time-domain or frequency-domain information of the EEG, as well as bi-channel features that reveal channel-wise relationships across brain regions. Despite these efforts, the mechanism of mutual interactions between EEG rhythms under different emotional expressions remains largely unexplored. Currently, the primary form of information interaction between EEG rhythms is phase-amplitude coupling (PAC), which results in computational complexity and high computational cost. (2) Methods: To address this issue, we proposed a method of extracting inter-bands correlation (IBC) features via canonical correlation analysis (CCA) based on differential entropy (DE) features. This approach eliminates the need for surrogate testing and reduces computational complexity. (3) Results: Our experiments verified the effectiveness of IBC features through several tests, demonstrating that the more correlated features between EEG frequency bands contribute more to emotion classification accuracy. We then fused IBC features and traditional DE features at the decision level, which significantly improved the accuracy of emotion recognition on the SEED dataset and the local CUMULATE dataset compared to using a single feature alone. (4) Conclusions: These findings suggest that IBC features are a promising approach to promoting emotion recognition accuracy. By exploring the mutual interactions between EEG rhythms under different emotional expressions, our method can provide valuable insights into the underlying mechanisms of emotion processing and improve the performance of emotion recognition systems.

Neural oscillations reflect the individual differences in the temporal perception of audiovisual speech.

Multisensory integration occurs within a limited time interval between multimodal stimuli. Multisensory temporal perception varies widely among individuals and involves perceptual synchrony and temporal sensitivity processes. Previous studies explored the neural mechanisms of individual differences for beep-flash stimuli, whereas there was no study for speech. In this study, 28 subjects (16 male) performed an audiovisual speech/ba/simultaneity judgment task while recording their electroencephalography. We examined the relationship between prestimulus neural oscillations (i.e. the pre-pronunciation movement-related oscillations) and temporal perception. The perceptual synchrony was quantified using the Point of Subjective Simultaneity and temporal sensitivity using the Temporal Binding Window. Our results revealed dissociated neural mechanisms for individual differences in Temporal Binding Window and Point of Subjective Simultaneity. The frontocentral delta power, reflecting top-down attention control, is positively related to the magnitude of individual auditory leading Temporal Binding Windows (auditory Temporal Binding Windows; LTBWs), whereas the parieto-occipital theta power, indexing bottom-up visual temporal attention specific to speech, is negatively associated with the magnitude of individual visual leading Temporal Binding Windows (visual Temporal Binding Windows; RTBWs). In addition, increased left frontal and bilateral temporoparietal occipital alpha power, reflecting general attentional states, is associated with increased Points of Subjective Simultaneity. Strengthening attention abilities might improve the audiovisual temporal perception of speech and further impact speech integration.

Beyond alpha band: prestimulus local oscillation and interregional synchrony of the beta band shape the temporal perception of the audiovisual beep-flash stimulus.

OBJECTIVE: Sensory integration is modulated by local prestimulus ongoing oscillatory activity which was suggested to play a role in organizing general neural processes such as attention and neuronal excitability and relatively longer inter-areal poststimulus phase coupling, especially in the 8-12 Hz alpha band. Previous work has examined the modulation effect of phase in audiovisual temporal integration, but there is no unified conclusion whether there is phasic modulation in the visual leading condition (sound-flash pairs). Moreover, it is unknown whether temporal integration is also subject to prestimulus inter-areal phase coupling between localizer-defined auditory and visual regions. APPROACH: Here, we recorded brain activity with EEG while human participants of both sexes performed a simultaneity judgment (SJ) task with the beep-flash stimuli to explore the functional role of the ongoing local oscillation and inter-areal coupling in temporal integration. Main results: We found that the power and ITC of the alpha-band are larger in synchronous response in both the visual and auditory leading conditions in their respective occipital and central channels, suggesting that neuronal excitability and attention play a role in temporal integration. Critically, the simultaneous judgment was modulated by the phases of low beta (14-20 Hz) oscillations quantified by the phase bifurcation index (PBI). Posthoc Rayleigh test indicated that the beta phase encodes different time information rather than neuronal excitability. Furthermore, we also found the stronger spontaneous high beta (21-28 Hz) phasic coupling between audiovisual cortices for synchronous response in auditory leading condition. SIGNIFICANCE: Together, these results demonstrate that spontaneous local low-frequency (< 30 Hz) neural oscillations and functional connectivity between auditory and visual brain regions especially in the beta band collectively influence audiovisual temporal integration. .

A Wireless, High-Quality, Soft and Portable Wrist-Worn System for sEMG Signal Detection.

The study of wearable systems based on surface electromyography (sEMG) signals has attracted widespread attention and plays an important role in human-computer interaction, physiological state monitoring, and other fields. Traditional sEMG signal acquisition systems are primarily targeted at body parts that are not in line with daily wearing habits, such as the arms, legs, and face. In addition, some systems rely on wired connections, which impacts their flexibility and user-friendliness. This paper presents a novel wrist-worn system with four sEMG acquisition channels and a high common-mode rejection ratio (CMRR) greater than 120 dB. The circuit has an overall gain of 2492 V/V and a bandwidth of 15~500 Hz. It is fabricated using flexible circuit technologies and is encapsulated in a soft skin-friendly silicone gel. The system acquires sEMG signals at a sampling rate of over 2000 Hz with a 16-bit resolution and transmits data to a smart device via low-power Bluetooth. Muscle fatigue detection and four-class gesture recognition experiments (accuracy greater than 95%) were conducted to validate its practicality. The system has potential applications in natural and intuitive human-computer interaction and physiological state monitoring.

Event-related potential patterns of selective attention modulated by perceptual load.

INTRODUCTION: A high perceptual load can effectively prevent attention from being drawn to irrelevant stimuli; however, the neural pattern underlying this process remains unclear. METHODS: This study adopted a perceptual load paradigm to examine the temporal processes of attentional modulation by incorporating conditions of perceptual load, distractor-target compatibility, and eccentricity. RESULTS: The behavioral results showed that a high perceptual load significantly reduced attentional distraction caused by peripheral distractors. The event-related potential results further revealed that shorter P2 latencies were observed for peripheral distractors than for central distractors under a high perceptual load and that a suppressed compatibility effect with increasing load was reflected by the P3 component. CONCLUSION: These findings suggested that (1) P2 and P3 components effectively captured different sides of attentional processing modulated by load (i.e., the filter processing of the object and the overall attentional resource allocation) and (2) response patterns of selective attention modulated by perceptual load were influenced by eccentricity. Our electrophysiological evidence confirmed the behavioral findings, indicating the neural mechanisms of attentional modulation.

The effect of prestimulus low-frequency neural oscillations on the temporal perception of audiovisual speech.

Objective: Perceptual integration and segregation are modulated by the phase of ongoing neural oscillation whose frequency period is broader than the size of the temporal binding window (TBW). Studies have shown that the abstract beep-flash stimuli with about 100 ms TBW were modulated by the alpha band phase. Therefore, we hypothesize that the temporal perception of speech with about hundreds of milliseconds of TBW might be affected by the delta-theta phase. Methods: Thus, we conducted a speech-stimuli-based audiovisual simultaneity judgment (SJ) experiment. Twenty human participants (12 females) attended this study, recording 62 channels of EEG. Results: Behavioral results showed that the visual leading TBWs are broader than the auditory leading ones [273.37 ± 24.24 ms vs. 198.05 ± 19.28 ms, (mean ± sem)]. We used Phase Opposition Sum (POS) to quantify the differences in mean phase angles and phase concentrations between synchronous and asynchronous responses. The POS results indicated that the delta-theta phase was significantly different between synchronous and asynchronous responses in the A50V condition (50% synchronous responses in auditory leading SOA). However, in the V50A condition (50% synchronous responses in visual leading SOA), we only found the delta band effect. In the two conditions, we did not find a consistency of phases over subjects for both perceptual responses by the post hoc Rayleigh test (all ps > 0.05). The Rayleigh test results suggested that the phase might not reflect the neuronal excitability which assumed that the phases within a perceptual response across subjects concentrated on the same angle but were not uniformly distributed. But V-test showed the phase difference between synchronous and asynchronous responses across subjects had a significant phase opposition (all ps < 0.05) which is compatible with the POS result. Conclusion: These results indicate that the speech temporal perception depends on the alignment of stimulus onset with an optimal phase of the neural oscillation whose frequency period might be broader than the size of TBW. The role of the oscillatory phase might be encoding the temporal information which varies across subjects rather than neuronal excitability. Given the enriched temporal structures of spoken language stimuli, the conclusion that phase encodes temporal information is plausible and valuable for future research.

Classification of EEG Signals Based on Sparrow Search Algorithm-Deep Belief Network for Brain-Computer Interface.

In brain-computer interface (BCI) systems, challenges are presented by the recognition of motor imagery (MI) brain signals. Established recognition approaches have achieved favorable performance from patterns like SSVEP, AEP, and P300, whereas the classification methods for MI need to be improved. Hence, seeking a classification method that exhibits high accuracy and robustness for application in MI-BCI systems is essential. In this study, the Sparrow search algorithm (SSA)-optimized Deep Belief Network (DBN), called SSA-DBN, is designed to recognize the EEG features extracted by the Empirical Mode Decomposition (EMD). The performance of the DBN is enhanced by the optimized hyper-parameters obtained through the SSA. Our method's efficacy was tested on three datasets: two public and one private. Results indicate a relatively high accuracy rate, outperforming three baseline methods. Specifically, on the private dataset, our approach achieved an accuracy of 87.83%, marking a significant 10.38% improvement over the standard DBN algorithm. For the BCI IV 2a dataset, we recorded an accuracy of 86.14%, surpassing the DBN algorithm by 9.33%. In the SMR-BCI dataset, our method attained a classification accuracy of 87.21%, which is 5.57% higher than that of the conventional DBN algorithm. This study demonstrates enhanced classification capabilities in MI-BCI, potentially contributing to advancements in the field of BCI.

A novel silent speech recognition approach based on parallel inception convolutional neural network and Mel frequency spectral coefficient.

Silent speech recognition breaks the limitations of automatic speech recognition when acoustic signals cannot be produced or captured clearly, but still has a long way to go before being ready for any real-life applications. To address this issue, we propose a novel silent speech recognition framework based on surface electromyography (sEMG) signals. In our approach, a new deep learning architecture Parallel Inception Convolutional Neural Network (PICNN) is proposed and implemented in our silent speech recognition system, with six inception modules processing six channels of sEMG data, separately and simultaneously. Meanwhile, Mel Frequency Spectral Coefficients (MFSCs) are employed to extract speech-related sEMG features for the first time. We further design and generate a 100-class dataset containing daily life assistance demands for the elderly and disabled individuals. The experimental results obtained from 28 subjects confirm that our silent speech recognition method outperforms state-of-the-art machine learning algorithms and deep learning architectures, achieving the best recognition accuracy of 90.76%. With sEMG data collected from four new subjects, efficient steps of subject-based transfer learning are conducted to further improve the cross-subject recognition ability of the proposed model. Promising results prove that our sEMG-based silent speech recognition system could have high recognition accuracy and steady performance in practical applications.

Vision-Language Navigation With Beam-Constrained Global Normalization.

Vision-language navigation (VLN) is a challenging task, which guides an agent to navigate in a realistic environment by natural language instructions. Sequence-to-sequence modeling is one of the most prospective architectures for the task, which achieves the agent navigation goal by a sequence of moving actions. The line of work has led to the state-of-the-art performance. Recently, several studies showed that the beam-search decoding during the inference can result in promising performance, as it ranks multiple candidate trajectories by scoring each trajectory as a whole. However, the trajectory-level score might be seriously biased during ranking. The score is a simple averaging of individual unit scores of the target-sequence actions, and these unit scores could be incomparable among different trajectories since they are calculated by a local discriminant classifier. To address this problem, we propose a global normalization strategy to rescale the scores at the trajectory level. Concretely, we present two global score functions to rerank all candidates in the output beam, resulting in more comparable trajectory scores. In this way, the bias problem can be greatly alleviated. We conduct experiments on the benchmark room-to-room (R2R) dataset of VLN to verify our method, and the results show that the proposed global method is effective, providing significant performance than the corresponding baselines. Our final model can achieve competitive performance on the VLN leaderboard.

Spatial localization in target detection based on decoding N2pc component.

BACKGROUND: The Gaze-independent BCI system is used to restore communication in patients with eye movement disorders. One available control mechanism is the utilization of spatial attention. However, spatial information is mostly used to simply answer the "True/False" target recognition question and is seldom used to improve the efficiency of target detection. Therefore, it is necessary to utilize the potential advantages of spatial attention to improving the target detection efficiency. NEW METHOD: We found that N2pc could be used to assess spatial attention shift and determine target position. It was a negative wave in the posterior brain on the contralateral target stimulus. From this, we designed a novel spatial coding paradigm to achieve two main purposes at each stimulus presentation: target recognition and spatial localization. COMPARISON WITH EXISTING METHODS: We used a two-step classification framework to decode the P300 and N2pc components. RESULTS: The average decoding accuracy of fourteen subjects was 84.43% (σ = 1.14%), and the classification accuracy of six subjects was more than 85%. The information transfer rate of the spatial coding paradigm could reach 60.52 bits/min. Compared with the single stimulus paradigm, the target detection efficiency was successfully improved by approximately 10%. CONCLUSIONS: The spatial coding paradigm proposed in this paper answered both "True/False" and "Left/Right" questions by decoding spatial attention information. This method could significantly improve image detection efficiencies, such as visual search tasks, Internet image screening, or military target determination.

A Tensor-Based Frequency Features Combination Method for Brain-Computer Interfaces.

With the development of the brain-computer interface (BCI) community, motor imagery-based BCI system using electroencephalogram (EEG) has attracted increasing attention because of its portability and low cost. Concerning the multi-channel EEG, the frequency component is one of the most critical features. However, insufficient extraction hinders the development and application of MI-BCIs. To deeply mine the frequency information, we proposed a method called tensor-based frequency feature combination (TFFC). It combined tensor-to-vector projection (TVP), fast fourier transform (FFT), common spatial pattern (CSP) and feature fusion to construct a new feature set. With two datasets, we used different classifiers to compare TFFC with the state-of-the-art feature extraction methods. The experimental results showed that our proposed TFFC could robustly improve the classification accuracy of about 5% ( ). Moreover, visualization analysis implied that the TFFC was a generalization of CSP and Filter Bank CSP (FBCSP). Also, a complementarity between weighted narrowband features (wNBFs) and broadband features (BBFs) was observed from the averaged fusion ratio. This article certificates the importance of frequency information in the MI-BCI system and provides a new direction for designing a feature set of MI-EEG.

Parallel-Inception CNN Approach for Facial sEMG based Silent Speech Recognition.

With the purpose of providing an external human-machine interaction platform for the elderly in need, a novel facial surface electromyography based silent speech recognition system was developed. In this study, we propose a deep learning architecture named Parallel-Inception Convolutional Neural Network (PICNN), and employ up-to-date feature extraction method log Mel frequency spectral coefficients (MFSC). To better meet the requirements of our target users, a 100-class dataset containing daily life-related demands was designed and generated for the comparative experiments. According to experimental results, the highest recognition accuracy of 88.44% was achieved by proposed recognition framework based on MFSC and PICNN, exceeding the performance of state-of-the-art deep learning algorithms such as CNN, VGGNet and Inception CNN (3.22%, 4.09% and 1.19%, respectively). These findings suggest that the newly developed silent speech approach holds promise to provide a more reliable communication channel, and the application scenery of speech recognition technology has been expanded at the same time.