<title>Spectral conversion algorithm from weighted median to stack filter</title>

Design of English text-to-speech conversion algorithm based on machine learning

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189238 ◽

2020 ◽

pp. 1-12

Author(s):

Li Dongmei

Keyword(s):

Machine Learning ◽

Speech Synthesis ◽

Feature Recognition ◽

Learning Algorithm ◽

Morphological Structure ◽

English Text ◽

Text To Speech ◽

Part Of Speech ◽

Modern Computer ◽

Conversion Algorithm

English text-to-speech conversion is the key content of modern computer technology research. Its difficulty is that there are large errors in the conversion process of text-to-speech feature recognition, and it is difficult to apply the English text-to-speech conversion algorithm to the system. In order to improve the efficiency of the English text-to-speech conversion, based on the machine learning algorithm, after the original voice waveform is labeled with the pitch, this article modifies the rhythm through PSOLA, and uses the C4.5 algorithm to train a decision tree for judging pronunciation of polyphones. In order to evaluate the performance of pronunciation discrimination method based on part-of-speech rules and HMM-based prosody hierarchy prediction in speech synthesis systems, this study constructed a system model. In addition, the waveform stitching method and PSOLA are used to synthesize the sound. For words whose main stress cannot be discriminated by morphological structure, label learning can be done by machine learning methods. Finally, this study evaluates and analyzes the performance of the algorithm through control experiments. The results show that the algorithm proposed in this paper has good performance and has a certain practical effect.

Download Full-text

Color space conversion algorithm of generalized regression neural network based on digital proof

Journal of Computer Applications ◽

10.3724/sp.j.1087.2010.02108 ◽

2010 ◽

Vol 30 (8) ◽

pp. 2108-2110

Author(s):

Cong-jun CAO ◽

Jing SUN

Keyword(s):

Neural Network ◽

Color Space ◽

Generalized Regression Neural Network ◽

Color Space Conversion ◽

Conversion Algorithm ◽

Generalized Regression

Download Full-text

Life Course Adiposity and Alzheimer’s Disease: A Mendelian Randomization Study

Journal of Alzheimer s Disease ◽

10.3233/jad-210345 ◽

2021 ◽

pp. 1-10

Author(s):

Xian Li ◽

Yan Tian ◽

Yu-Xiang Yang ◽

Ya-Hui Ma ◽

Xue-Ning Shen ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Life Course ◽

Mendelian Randomization ◽

Association Studies ◽

Meta Analysis ◽

Genome Wide Association Studies ◽

Fat Percentage ◽

Regression Methods ◽

Weighted Median

Background: Several studies showed that life course adiposity was associated with Alzheimer’s disease (AD). However, the underlying causality remains unclear. Objective: We aimed to examine the causal relationship between life course adiposity and AD using Mendelian randomization (MR) analysis. Methods: Instrumental variants were obtained from large genome-wide association studies (GWAS) for life course adiposity, including birth weight (BW), childhood body mass index (BMI), adult BMI, waist circumference (WC), waist-to-hip ratio (WHR), and body fat percentage (BFP). A meta-analysis of GWAS for AD including 71,880 cases and 383,378 controls was used in this study. MR analyses were performed using inverse variance weighted (IVW), weighted median, and MR-Egger regression methods. We calculated odds ratios (ORs) per genetically predicted standard deviation (1-SD) unit increase in each trait for AD. Results: Genetically predicted 1-SD increase in adult BMI was significantly associated with higher risk of AD (IVW: OR = 1.03, 95% confidence interval [CI] = 1.01–1.05, p = 2.7×10–3) after Bonferroni correction. The weighted median method indicated a significant association between BW and AD (OR = 0.94, 95% CI = 0.90–0.98, p = 1.8×10–3). We also found suggestive associations of AD with WC (IVW: OR = 1.03, 95% CI = 1.00–1.07, p = 0.048) and WHR (weighted median: OR = 1.04, 95% CI = 1.00–1.07, p = 0.029). No association was detected of AD with childhood BMI and BFP. Conclusion: Our study demonstrated that lower BW and higher adult BMI had causal effects on increased AD risk.

Download Full-text

A Mendelian randomization analysis of the relationship between cardioembolic risk factors and ischemic stroke

Scientific Reports ◽

10.1038/s41598-021-93979-y ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Danyang Tian ◽

Linjing Zhang ◽

Zhenhuang Zhuang ◽

Tao Huang ◽

Dongsheng Fan

Keyword(s):

Risk Factors ◽

Ischemic Stroke ◽

Mendelian Randomization ◽

P Wave ◽

Cardioembolic Stroke ◽

Large Artery ◽

Weighted Analysis ◽

Inverse Variance ◽

Weighted Median ◽

Genetically Determined

AbstractObservational studies have shown that several risk factors are associated with cardioembolic stroke. However, whether such associations reflect causality remains unknown. We aimed to determine whether established and provisional cardioembolic risk factors are causally associated with cardioembolic stroke. Genetic instruments for atrial fibrillation (AF), myocardial infarction (MI), electrocardiogram (ECG) indices and N-terminal pro-brain natriuretic peptide (NT-pro BNP) were obtained from large genetic consortiums. Summarized data of ischemic stroke and its subtypes were extracted from the MEGASTROKE consortium. Causal estimates were calculated by applying inverse-variance weighted analysis, weighted median analysis, simple median analysis and Mendelian randomization (MR)-Egger regression. Genetically predicted AF was significantly associated with higher odds of ischemic stroke (odds ratio (OR): 1.20, 95% confidence intervals (CI): 1.16–1.24, P = 6.53 × 10–30) and cardioembolic stroke (OR: 1.95, 95% CI: 1.85–2.06, P = 8.81 × 10–125). Suggestive associations were found between genetically determined resting heart rate and higher odds of ischemic stroke (OR: 1.01, 95% CI: 1.00–1.02, P = 0.005), large-artery atherosclerotic stroke (OR: 1.02, 95% CI: 1.00–1.04, P = 0.026) and cardioembolic stroke (OR: 1.02, 95% CI: 1.00–1.04, P = 0.028). There was no causal association of P‐wave terminal force in the precordial lead V1 (PTFVI), P-wave duration (PWD), NT-pro BNP or PR interval with ischemic stroke or any subtype.

Download Full-text