Attention mechanism based LSTM in classification of stressed speech under workload

2021 ◽  
Vol 25 (6) ◽  
pp. 1603-1627
Author(s):  
Xiao Yao ◽  
Zhengyan Sheng ◽  
Min Gu ◽  
Haibin Wang ◽  
Ning Xu ◽  
...  
Keyword(s):  
Feature Fusion ◽  
Small Sample ◽  
Attention Mechanism ◽  
Fusion Model ◽  
Speech Corpus ◽  
Traditional Methods ◽  
Transient Nature ◽  
Stress Classification ◽  
Proposed Model ◽  
Small Sample Sizes

In order to improve the robustness of speech recognition systems, this study attempts to classify stressed speech caused by the psychological stress under multitasking workloads. Due to the transient nature and ambiguity of stressed speech, the stress characteristics is not represented in all the segments in stressed speech as labeled. In this paper, we propose a multi-feature fusion model based on the attention mechanism to measure the importance of segments for stress classification. Through the attention mechanism, each speech frame is weighted to reflect the different correlations to the actual stressed state, and the multi-channel fusion of features characterizing the stressed speech to classify the speech under stress. The proposed model further adopts SpecAugment in view of the feature spectrum for data augment to resolve small sample sizes problem among stressed speech. During the experiment, we compared the proposed model with traditional methods on CASIA Chinese emotion corpus and Fujitsu stressed speech corpus, and results show that the proposed model has better performance in speaker-independent stress classification. Transfer learning is also performed for speaker-dependent classification for stressed speech, and the performance is improved. The attention mechanism shows the advantage for continuous speech under stress in authentic context comparing with traditional methods.

scholarly journals Feature Fusion Text Classification Model Combining CNN and BiGRU with Multi-Attention Mechanism

2019 ◽  
Vol 11 (11) ◽  
pp. 237
Author(s):  
Jingren Zhang ◽  
Fang’ai Liu ◽  
Weizhi Xu ◽  
Hui Yu
Keyword(s):  
Natural Language ◽  
Short Term Memory ◽  
Feature Fusion ◽  
Attention Mechanism ◽  
Sentiment Classification ◽  
Classification Model ◽  
Fusion Model ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Convolutional neural networks (CNN) and long short-term memory (LSTM) have gained wide recognition in the field of natural language processing. However, due to the pre- and post-dependence of natural language structure, relying solely on CNN to implement text categorization will ignore the contextual meaning of words and bidirectional long short-term memory (BiLSTM). The feature fusion model is divided into a multiple attention (MATT) CNN model and a bi-directional gated recurrent unit (BiGRU) model. The CNN model inputs the word vector (word vector attention, part of speech attention, position attention) that has been labeled by the attention mechanism into our multi-attention mechanism CNN model. Obtaining the influence intensity of the target keyword on the sentiment polarity of the sentence, and forming the first dimension of the sentiment classification, the BiGRU model replaces the original BiLSTM and extracts the global semantic features of the sentence level to form the second dimension of sentiment classification. Then, using PCA to reduce the dimension of the two-dimensional fusion vector, we finally obtain a classification result combining two dimensions of keywords and sentences. The experimental results show that the proposed MATT-CNN+BiGRU fusion model has 5.94% and 11.01% higher classification accuracy on the MRD and SemEval2016 datasets, respectively, than the mainstream CNN+BiLSTM method.

Integrating Visual and Bayesian Statistical Analyses in Single Case Experimental Research to Evaluate the Effectiveness and Magnitude of a Comprehensive Behavioral Intervention

2018 ◽  
Author(s):  
Prathiba Natesan ◽  
Smita Mehta
Keyword(s):  
Behavioral Intervention ◽  
Effect Size ◽  
Rate Ratio ◽  
Visual Analysis ◽  
Single Case ◽  
Small Sample ◽  
Statistical Analyses ◽  
Data Types ◽  
Ratio Effect ◽  
Small Sample Sizes

Single case experimental designs (SCEDs) have become an indispensable methodology where randomized control trials may be impossible or even inappropriate. However, the nature of SCED data presents challenges for both visual and statistical analyses. Small sample sizes, autocorrelations, data types, and design types render many parametric statistical analyses and maximum likelihood approaches ineffective. The presence of autocorrelation decreases interrater reliability in visual analysis. The purpose of the present study is to demonstrate a newly developed model called the Bayesian unknown change-point (BUCP) model which overcomes all the above-mentioned data analytic challenges. This is the first study to formulate and demonstrate rate ratio effect size for autocorrelated data, which has remained an open question in SCED research until now. This expository study also compares and contrasts the results from BUCP model with visual analysis, and rate ratio effect size with nonoverlap of all pairs (NAP) effect size. Data from a comprehensive behavioral intervention are used for the demonstration.

No Evidence that Experiencing Physical Warmth Promotes Interpersonal Warmth: Two Failures to Replicate Williams and Bargh (2008)

2018 ◽  
Author(s):  
Christopher Chabris ◽  
Patrick Ryan Heck ◽  
Jaclyn Mandart ◽  
Daniel Jacob Benjamin ◽  
Daniel J. Simons
Keyword(s):  
Null Hypothesis ◽  
Small Sample ◽  
Sample Sizes ◽  
Double Blind ◽  
Bayesian Analyses ◽  
Physical Warmth ◽  
Small Sample Sizes ◽  
Interpersonal Warmth

Williams and Bargh (2008) reported that holding a hot cup of coffee caused participants to judge a person’s personality as warmer, and that holding a therapeutic heat pad caused participants to choose rewards for other people rather than for themselves. These experiments featured large effects (r = .28 and .31), small sample sizes (41 and 53 participants), and barely statistically significant results. We attempted to replicate both experiments in field settings with more than triple the sample sizes (128 and 177) and double-blind procedures, but found near-zero effects (r = –.03 and .02). In both cases, Bayesian analyses suggest there is substantially more evidence for the null hypothesis of no effect than for the original physical warmth priming hypothesis.

scholarly journals Non-Invasive Monitoring of Adrenocortical Activity in Three Sympatric Desert Gerbil Species

Animals ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 75
Author(s):  
Álvaro Navarro-Castilla ◽  
Mario Garrido ◽  
Hadas Hawlena ◽  
Isabel Barja
Keyword(s):  
Small Sample ◽  
Post Injection ◽  
Control Groups ◽  
Treatment Groups ◽  
Adrenocortical Activity ◽  
Non Invasive ◽  
Endocrine Status ◽  
Corticosterone Metabolites ◽  
Small Sample Sizes ◽  
Fecal Corticosterone Metabolites

The study of the endocrine status can be useful to understand wildlife responses to the changing environment. Here, we validated an enzyme immunoassay (EIA) to non-invasively monitor adrenocortical activity by measuring fecal corticosterone metabolites (FCM) in three sympatric gerbil species (Gerbillus andersoni, G. gerbillus and G. pyramidum) from the Northwestern Negev Desert’s sands (Israel). Animals included into treatment groups were injected with adrenocorticotropic hormone (ACTH) to stimulate adrenocortical activity, while control groups received a saline solution. Feces were collected at different intervals and FCM were quantified by an EIA. Basal FCM levels were similar in the three species. The ACTH effect was evidenced, but the time of FCM peak concentrations appearance differed between the species (6–24 h post-injection). Furthermore, FCM peak values were observed sooner in G. andersoni females than in males (6 h and 18 h post-injection, respectively). G. andersoni and G. gerbillus males in control groups also increased FCM levels (18 h and 48 h post-injection, respectively). Despite the small sample sizes, our results confirmed the EIA suitability for analyzing FCM in these species as a reliable indicator of the adrenocortical activity. This study also revealed that close species, and individuals within a species, can respond differently to the same stressor.

scholarly journals Use of Antiplatelet Agents Decreases the Positive Predictive Value of Fecal Immunochemical Tests for Colorectal Cancer but Does Not Affect Their Sensitivity

2021 ◽  
Vol 11 (6) ◽  
pp. 497
Author(s):  
Yoonsuk Jung ◽  
Eui Im ◽  
Jinhee Lee ◽  
Hyeah Lee ◽  
Changmo Moon
Keyword(s):  
Colorectal Cancer ◽  
Large Scale ◽  
Screening Program ◽  
Antiplatelet Agents ◽  
Population Based ◽  
Small Sample ◽  
Antithrombotic Agents ◽  
Predictive Values ◽  
Prescription Rates ◽  
Small Sample Sizes

Previous studies have evaluated the effects of antithrombotic agents on the performance of fecal immunochemical tests (FITs) for the detection of colorectal cancer (CRC), but the results were inconsistent and based on small sample sizes. We studied this topic using a large-scale population-based database. Using the Korean National Cancer Screening Program Database, we compared the performance of FITs for CRC detection between users and non-users of antiplatelet agents and warfarin. Non-users were matched according to age and sex. Among 5,426,469 eligible participants, 768,733 used antiplatelet agents (mono/dual/triple therapy, n = 701,683/63,211/3839), and 19,569 used warfarin, while 4,638,167 were non-users. Among antiplatelet agents, aspirin, clopidogrel, and cilostazol ranked first, second, and third, respectively, in terms of prescription rates. Users of antiplatelet agents (3.62% vs. 4.45%; relative risk (RR): 0.83; 95% confidence interval (CI): 0.78–0.88), aspirin (3.66% vs. 4.13%; RR: 0.90; 95% CI: 0.83–0.97), and clopidogrel (3.48% vs. 4.88%; RR: 0.72; 95% CI: 0.61–0.86) had lower positive predictive values (PPVs) for CRC detection than non-users. However, there were no significant differences in PPV between cilostazol vs. non-users and warfarin users vs. non-users. For PPV, the RR (users vs. non-users) for antiplatelet monotherapy was 0.86, while the RRs for dual and triple antiplatelet therapies (excluding cilostazol) were 0.67 and 0.22, respectively. For all antithrombotic agents, the sensitivity for CRC detection was not different between users and non-users. Use of antiplatelet agents, except cilostazol, may increase the false positives without improving the sensitivity of FITs for CRC detection.

scholarly journals Perioperative digital behaviour change interventions for reducing alcohol consumption, improving dietary intake, increasing physical activity and smoking cessation: a scoping review

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Katarina Åsberg ◽  
Marcus Bendtsen
Keyword(s):  
Physical Activity ◽  
Smoking Cessation ◽  
Behaviour Change ◽  
Scoping Review ◽  
Text Messaging ◽  
Text Message ◽  
Feasibility Studies ◽  
Small Sample ◽  
Small Sample Sizes ◽  
Randomised Controlled

Abstract Background Evidence suggests that unhealthy lifestyle behaviours are modifiable risk factors for postoperative complications. Digital behaviour change interventions (DBCIs), for instance text messaging programs and smartphone apps, have shown promise in achieving lifestyle behaviour change in a wide range of clinical populations, and it may therefore be possible to reduce postoperative complications by supporting behaviour change perioperatively using digital interventions. This scoping review was conducted in order to identify existing research done in the area of perioperative DBCIs for reducing alcohol consumption, improving dietary intake, increasing physical activity and smoking cessation. Main text This scoping review included eleven studies covering a range of surgeries: bariatric, orthopaedic, cancer, transplantation and elective surgery. The studies were both randomised controlled trials and feasibility studies and investigated a diverse set of interventions: one game, three smartphone apps, one web-based program and five text message interventions. Feasibility studies reported user acceptability and satisfaction with the behaviour change support. Engagement data showed participation rates ranged from 40 to 90%, with more participants being actively engaged early in the intervention period. In conclusion, the only full-scale randomised controlled trial (RCT), text messaging ahead of bariatric surgery did not reveal any benefits with respect to adherence to preoperative exercise advice when compared to a control group. Two of the pilot studies, one text message intervention, one game, indicated change in a positive direction with respect to alcohol and tobacco outcomes, but between group comparisons were not done due to small sample sizes. The third pilot-study, a smartphone app, found between group changes for physical activity and alcohol, but not with respect to smoking cessation outcomes. Conclusion This review found high participant satisfaction, but shows recruitment and timing-delivery issues, as well as low retention to interventions post-surgery. Small sample sizes and the use of a variety of feasibility outcome measures prevent the synthesis of results and makes generalisation difficult. Future research should focus on defining standardised outcome measures, enhancing patient engagement and improving adherence to behaviour change prior to scheduled surgery.

Sign in / Sign up

Export Citation Format

Share Document