scholarly journals Neural Network Modelling of Speech Emotion Detection

2021 ◽  
Vol 309 ◽  
pp. 01139
Author(s):  
Y. Sri Lalitha ◽  
Althaf Hussain Basha Sk ◽  
M. V. Aditya Nag
Keyword(s):  
Speech Recognition ◽  
Point Of View ◽  
Emotion Detection ◽  
Network Modelling ◽  
Emotion Identification ◽  
Essential Requirement ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Types Of Information ◽  
Improved Accuracy

In making the Machines Intelligent, and enable them to work as human, Speech recognition is one of the most essential requirement. Human Language conveys various types of information such as the energy, pitch, loudness, rhythm etc., in the sound, the speech and its context such as gender, age and the emotion. Identifying the emotion from a speech pattern is a challenging task and the most useful solution especially in the era of widely developing speech recognition systems with digital assistants. Digital assistants like Bixby, Blackberry assistant are building products that consist of emotion identification and reply the user in step with user point of view. The objective of this work is to improve the accuracy of the speech emotion prediction using deep learning models. Our work experiments with the MLP and CNN classification models on three benchmark datasets with 5700 speech files of 7 emotion categories. The proposed model showed improved accuracy.

scholarly journals Jointly Multiple Hash Learning

2019 ◽  
Vol 33 ◽  
pp. 9981-9982
Author(s):  
Xingbo Liu ◽  
Xiushan Nie ◽  
Yingxin Wang ◽  
Yilong Yin
Keyword(s):  
Superior Performance ◽  
Closed Form Solutions ◽  
Fixed Length ◽  
Compact Binary ◽  
Proposed Model ◽  
Efficient Retrieval ◽  
Benchmark Datasets ◽  
One Step ◽  
Types Of Information ◽  
Hash Codes

Hashing can compress heterogeneous high-dimensional data into compact binary codes while preserving the similarity to facilitate efficient retrieval and storage, and thus hashing has recently received much attention from information retrieval researchers. Most of the existing hashing methods first predefine a fixed length (e.g., 32, 64, or 128 bit) for the hash codes before learning them with this fixed length. However, one sample can be represented by various hash codes with different lengths, and thus there must be some associations and relationships among these different hash codes because they represent the same sample. Therefore, harnessing these relationships will boost the performance of hashing methods. Inspired by this possibility, in this study, we propose a new model jointly multiple hash learning (JMH), which can learn hash codes with multiple lengths simultaneously. In the proposed JMH method, three types of information are used for hash learning, which come from hash codes with different lengths, the original features of the samples and label. In contrast to the existing hashing methods, JMH can learn hash codes with different lengths in one step. Users can select appropriate hash codes for their retrieval tasks according to the requirements in terms of accuracy and complexity. To the best of our knowledge, JMH is one of the first attempts to learn multi-length hash codes simultaneously. In addition, in the proposed model, discrete and closed-form solutions for variables can be obtained by cyclic coordinate descent, thereby making the proposed model much faster during training. Extensive experiments were performed based on three benchmark datasets and the results demonstrated the superior performance of the proposed method.

Bioluminescent proteins prediction with voting strategy.

2020 ◽  
Vol 15 ◽  
Author(s):  
Shulin Zhao ◽  
Ying Ju ◽  
Xiucai Ye ◽  
Jun Zhang ◽  
Shuguang Han
Keyword(s):  
Amino Acid ◽  
Model Building ◽  
Prediction Method ◽  
Pair Composition ◽  
Proposed Model ◽  
Counting Rules ◽  
Significant Phenomenon ◽  
Voting Strategy ◽  
Improved Accuracy ◽  
Selection Of

Background: Bioluminescence is a unique and significant phenomenon in nature. Bioluminescence is important for the lifecycle of some organisms and is valuable in biomedical research, including for gene expression analysis and bioluminescence imaging technology.In recent years, researchers have identified a number of methods for predicting bioluminescent proteins (BLPs), which have increased in accuracy, but could be further improved. Method: In this paper, we propose a new bioluminescent proteins prediction method based on a voting algorithm. We used four methods of feature extraction based on the amino acid sequence. We extracted 314 dimensional features in total from amino acid composition, physicochemical properties and k-spacer amino acid pair composition. In order to obtain the highest MCC value to establish the optimal prediction model, then used a voting algorithm to build the model.To create the best performing model, we discuss the selection of base classifiers and vote counting rules. Results: Our proposed model achieved 93.4% accuracy, 93.4% sensitivity and 91.7% specificity in the test set, which was better than any other method. We also improved a previous prediction of bioluminescent proteins in three lineages using our model building method, resulting in greatly improved accuracy.

scholarly journals Speech recognition algorithm for natural language management systems under variety of accents

2020 ◽  
Vol 164 ◽  
pp. 10015
Author(s):  
Irina Gurtueva ◽  
Olga Nagoeva ◽  
Inna Pshenokova
Keyword(s):  
Speech Recognition ◽  
Recognition Algorithm ◽  
Individual Characteristics ◽  
Point Of View ◽  
Language Management ◽  
Universal System ◽  
Sound Image ◽  
Behavioral Studies ◽  
Multi Agent ◽  
The Individual

This paper proposes a concept of a new approach to the development of speech recognition systems using multi-agent neurocognitive modeling. The fundamental foundations of these developments are based on the theory of cognitive psychology and neuroscience, and advances in computer science. The purpose of this work is the development of general theoretical principles of sound image recognition by an intelligent robot and, as the sequence, the development of a universal system of automatic speech recognition, resistant to speech variability, not only with respect to the individual characteristics of the speaker, but also with respect to the diversity of accents. Based on the analysis of experimental data obtained from behavioral studies, as well as theoretical model ideas about the mechanisms of speech recognition from the point of view of psycholinguistic knowledge, an algorithm resistant to variety of accents for machine learning with imitation of the formation of a person’s phonemic hearing has been developed.

Object-Oriented Analysis of an Information Model for Hull Piece Fabrication

1999 ◽  
Vol 15 (04) ◽  
pp. 207-221
Author(s):  
Jong Gye Shin ◽  
Won Don Kim
Keyword(s):  
Information Flow ◽  
Information Integration ◽  
Object Oriented ◽  
Information Model ◽  
Object Relation ◽  
Point Of View ◽  
Information Modeling ◽  
Product Model ◽  
Object Oriented Approach ◽  
Improved Accuracy

The production procedure of ship's hull plates includes hull modeling, lofting, cutting, and forming in sequence. Each process is isolated from the point of view of information flow and current practices in forming hull pieces are experience-dependent. This, in turn, reduces productivity and prevents the development of automation. To satisfy shipyards' demand for improved accuracy and enhanced productivity with mechanization or automation, it is necessary to collect production information, and to structure and maintain it in a well-organized manner. The objective of this paper is to propose an information model for ship's hull piece forming in a systematic manner. First, current shipyardsi practices and information flow relative to hull production process are described. From the point of view of information integration, the necessity of an information model is clarified. An information model for ship's hull piece forming is then proposed. For the information model, product model and concurrent engineering concepts are introduced. Since the construction of the information model with the two concepts requires an object-oriented approach, a new mixed-type, called here ‘hybrid’, object-oriented methodology for hull piece information model is defined. Based on the proposed methodology, the object association and operation analyses are carried out for the information modeling of hull piece forming. Through the analysis, the object-relation diagram shows that kinematics data is indispensable to construct the information model for hull piece forming.

scholarly journals Instance Enhancement Batch Normalization: An Adaptive Regulator of Batch Noise

2020 ◽  
Vol 34 (04) ◽  
pp. 4819-4827
Author(s):  
Senwei Liang ◽  
Zhongzhan Huang ◽  
Mingfu Liang ◽  
Haizhao Yang
Keyword(s):  
Input Image ◽  
Point Of View ◽  
Specific Information ◽  
Network Training ◽  
Batch Normalization ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
Adaptive Regulator ◽  
Batch Noise ◽  
Parameter Increment

Batch Normalization (BN) (Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but too much noise will harm the performance of networks. In our paper, we offer a new point of view that the self-attention mechanism can help to regulate the noise by enhancing instance-specific information to obtain a better regularization effect. Therefore, we propose an attention-based BN called Instance Enhancement Batch Normalization (IEBN) that recalibrates the information of each channel by a simple linear transformation. IEBN has a good capacity of regulating the batch noise and stabilizing network training to improve generalization even in the presence of two kinds of noise attacks during training. Finally, IEBN outperforms BN with only a light parameter increment in image classification tasks under different network structures and benchmark datasets.

scholarly journals ViraMiner: Deep Learning on Raw DNA Sequences for Identifying Viral Genomes in Human Samples

2019 ◽  
Author(s):  
Ardi Tampuu ◽  
Zurab Bzhalava ◽  
Joakim Dillner ◽  
Raul Vicente
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Dna Sequences ◽  
Recommendation System ◽  
Clinical Importance ◽  
Training Dataset ◽  
Viral Genomes ◽  
Human Samples ◽  
Types Of Information ◽  
Improved Accuracy

ABSTRACTDespite its clinical importance, detection of highly divergent or yet unknown viruses is a major challenge. When human samples are sequenced, conventional alignments classify many assembled contigs as “unknown” since many of the sequences are not similar to known genomes. In this work, we developed ViraMiner, a deep learning-based method to identify viruses in various human biospecimens. ViraMiner contains two branches of Convolutional Neural Networks designed to detect both patterns and pattern-frequencies on raw metagenomics contigs. The training dataset included sequences obtained from 19 metagenomic experiments which were analyzed and labeled by BLAST. The model achieves significantly improved accuracy compared to other machine learning methods for viral genome classification. Using 300 bp contigs ViraMiner achieves 0.923 area under the ROC curve. To our knowledge, this is the first machine learning methodology that can detect the presence of viral sequences among raw metagenomic contigs from diverse human samples. We suggest that the proposed model captures different types of information of genome composition, and can be used as a recommendation system to further investigate sequences labeled as “unknown” by conventional alignment methods. Exploring these highly-divergent viruses, in turn, can enhance our knowledge of infectious causes of diseases.

scholarly journals Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

2020 ◽  
Vol 34 (05) ◽  
pp. 7797-7804
Author(s):  
Goran Glavašš ◽  
Swapna Somasundaran
Keyword(s):  
State Of The Art ◽  
Language Transfer ◽  
Text Segmentation ◽  
Word Embeddings ◽  
Neural Architecture ◽  
Text Coherence ◽  
Sentence Level ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

scholarly journals Enzyme catalysis as a chain reaction

1991 ◽  
Vol 279 (3) ◽  
pp. 855-861 ◽  
Author(s):  
S E Szedlacsek ◽  
R G Duggleby ◽  
M O Vlad
Keyword(s):  
Reaction Mechanism ◽  
Kinetic Mechanism ◽  
Point Of View ◽  
Simple Type ◽  
Chain Reaction ◽  
Proposed Model ◽  
New Type ◽  
A Chain ◽  
Theoretical Considerations ◽  
Classical Mechanism

A new type of enzyme kinetic mechanism is suggested by which catalysis may be viewed as a chain reaction. A simple type of one-substrate/one-product reaction mechanism has been analysed from this point of view, and the kinetics, in both the transient and the steady-state phases, has been reconsidered. This analysis, as well as literature data and theoretical considerations, shows that the proposed model is a generalization of the classical ones. As a consequence of the suggested mechanism, the expressions, and in some cases even the significance of classical constants (Km and Vmax.), are altered. Moreover, this mechanism suggests that, between two successive enzyme-binding steps, more than one catalytic act could be accomplished. The reaction catalysed by alcohol dehydrogenase was analysed, and it was shown that this chain-reaction mechanism has a real contribution to the catalytic process, which could become exclusive under particular conditions. Similarly, the mechanism of glycogen phosphorylase is considered, and two partly modified versions of the classical mechanism are proposed. They account for both the existing experimental facts and suggest the possibility of chain-reaction pathways for any polymerase.

Sign in / Sign up

Export Citation Format

Share Document