Analysis of speech MEL scale and its classification as big data by parameterized KNN

2021 ◽  
Vol 26 (jai2021.26(1)) ◽  
pp. 42-57
Author(s):  
Skuratovskii R ◽  
◽  
Bazarna A ◽  
Osadhyy E ◽  
◽  
...  
Keyword(s):  
Human Perception ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Emotional States ◽  
Prosodic Features ◽  
Language Recognition ◽  
Human Speech ◽  
Classification Feature ◽  
Loaded Part ◽  
Learning Platforms

Recognizing emotions and human speech has always been an exciting challenge for scientists. In our work the parameterization of the vector is obtained and realized from the sentence divided into the containing emotional-informational part and the informational part is effectively applied. The expressiveness of human speech is improved by the emotion it conveys. There are several characteristics and features of speech that differentiate it among utterances, i.e. various prosodic features like pitch, timbre, loudness and vocal tone which categorize speech into several emotions. They were supplemented by us with a new classification feature of speech, which consists in dividing a sentence into an emotionally loaded part of the sentence and a part that carries only informational load. Therefore, the sample speech is changed when it is subjected to various emotional environments. As the identification of the speaker’s emotional states can be done based on the Mel scale, MFCC is one such variant to study the emotional aspects of a speaker’s utterances. In this work, we implement a model to identify several emotional states from MFCC for two datasets, classify emotions for them on the basis of MFCC features and give the correspondent comparison of them. Overall, this work implements the classification model based on dataset minimization that is done by taking the mean of features for the improvement of the classification accuracy rate in different machine learning algorithms. In addition to the static analysis of the author's tonal portrait, which is used in particular in MFFC, we propose a new method for the dynamic analysis of the phrase in processing and studying as a new linguistic-emotional entity pronounced by the same author. Due to the ranking by the importance of the MEL scale features, we are able to parameterize the vectors coordinates be processed by the parametrized KNN method. Language recognition is a multi-level task of pattern recognition. Here acoustic signals are analyzed and structured in a hierarchy of structural elements, words, phrases and sentences. Each level of such a hierarchy may provide some temporal constants: possible word sequences or known types of pronunciation that reduce the number of recognition errors at a lower level. An analysis of voice and speech dynamics is appropriate for improving the quality of human perception and the formation of human speech by a machine and is within the capabilities of artificial intelligence. Emotion results can be widely applied in e-learning platforms, vehicle on-board systems, medicine, etc

scholarly journals Big Data Classification for the Analysis MEL Scale Features Using KNN Parameterization

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Machine Learning Algorithms ◽  
Classification Model ◽  
Emotional States ◽  
Prosodic Features ◽  
Classification Feature ◽  
Emotional Aspects ◽  
Loaded Part ◽  
The Mean ◽  
Big Data Classification

The role of human speech is intensified by the emotion it conveys. The parameterization of the vector obtained from the sentence divided into the containing emotional-informational part and the informational part is effectively applied. There are several characteristics and features of speech that differentiate it among utterances, i.e. various prosodic features like pitch, timbre, loudness and vocal tone which categorize speech into several emotions. They were supplemented by us with a new classification feature of speech, which consists in dividing a sentence into an emotionally loaded part of the sentence and a part that carries only informational load. Therefore, the sample speech is changed when it is subjected to various emotional environments. As the identification of the speaker’s emotional states can be done based on the Mel scale, MFCC is one such variant to study the emotional aspects of a speaker’s utterances. In this work, we implement a model to identify several emotional states from MFCC for two datasets, classify emotions for them on the basis of MFCC features and give the comparison of both. Overall, this work implements the classification model based on dataset minimization that is done by taking the mean of features for the improvement of the classification accuracy rate in different machine learning algorithms.

Drug Target Group Prediction with Multiple Drug Networks

2020 ◽  
Vol 23 (4) ◽  
pp. 274-284 ◽  
Author(s):  
Jingang Che ◽  
Lei Chen ◽  
Zi-Han Guo ◽  
Shuaiqun Wang ◽  
Aorigele
Keyword(s):  
Drug Target ◽  
Low Cost ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Support Vector ◽  
Multiple Drug ◽  
Property A ◽  
Multiple Networks ◽  
Proposed Model ◽  
The One

Background: Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments. Methods: In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model. Results and Conclusion: Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

KArSL

2021 ◽  
Vol 20 (1) ◽  
pp. 1-19
Author(s):  
Ala Addin I. Sidig ◽  
Hamzah Luqman ◽  
Sabri Mahmoud ◽  
Mohamed Mohandes
Keyword(s):  
Deep Learning ◽  
Sign Language ◽  
Markov Models ◽  
Body Language ◽  
Arab Countries ◽  
Microsoft Kinect ◽  
Classification Model ◽  
Language Recognition ◽  
Sign Language Recognition ◽  
Arabic Sign Language

Sign language is the major means of communication for the deaf community. It uses body language and gestures such as hand shapes, lib patterns, and facial expressions to convey a message. Sign language is geography-specific, as it differs from one country to another. Arabic Sign language is used in all Arab countries. The availability of a comprehensive benchmarking database for ArSL is one of the challenges of the automatic recognition of Arabic Sign language. This article introduces KArSL database for ArSL, consisting of 502 signs that cover 11 chapters of ArSL dictionary. Signs in KArSL database are performed by three professional signers, and each sign is repeated 50 times by each signer. The database is recorded using state-of-art multi-modal Microsoft Kinect V2. We also propose three approaches for sign language recognition using this database. The proposed systems are Hidden Markov Models, deep learning images’ classification model applied on an image composed of shots of the video of the sign, and attention-based deep learning captioning system. Recognition accuracies of these systems indicate their suitability for such a large number of Arabic signs. The techniques are also tested on a publicly available database. KArSL database will be made freely available for interested researchers.

Spoken Language Recognition With Prosodic Features

2013 ◽  
Vol 21 (9) ◽  
pp. 1841-1853 ◽  
Author(s):  
Raymond W. M. Ng ◽  
Tan Lee ◽  
Cheung-Chi Leung ◽  
Bin Ma ◽  
Haizhou Li
Keyword(s):  
Spoken Language ◽  
Prosodic Features ◽  
Language Recognition

MONITORING AND CLASSIFYING THE STATE OF HARD DISKS USING RECURRENT NEURAL NETWORKS

2021 ◽  
pp. 36-43
Author(s):  
L. A. Demidova ◽  
A. V. Filatov
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Experimental Studies ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Dense Layer ◽  
Hard Disks ◽  
Destructive Testing ◽  
Data Set ◽  
State Classification

The article considers an approach to solving the problem of monitoring and classifying the states of hard disks, which is solved on a regular basis, within the framework of the concept of non-destructive testing. It is proposed to solve this problem by developing a classification model using machine learning algorithms, in particular, using recurrent neural networks with Simple RNN, LSTM and GRU architectures. To develop a classification model, a data set based on the values of SMART sensors installed on hard disks it used. It represents a group of multidimensional time series. At the same time, the structure of the classification model contains two layers of a neural network with one of the recurrent architectures, as well as a Dropout layer and a Dense layer. The results of experimental studies confirming the advantages of LSTM and GRU architectures as part of hard disk state classification models are presented.

Association of Snoring Characteristics with Predominant Site of Collapse of Upper Airway in Obstructive Sleep Apnoea Patients

SLEEP ◽  
2021 ◽  
Author(s):  
Arun Sebastian ◽  
Peter A Cistulli ◽  
Gary Cohen ◽  
Philip de Chazal
Keyword(s):  
Acoustic Analysis ◽  
Audio Signal ◽  
Upper Airway ◽  
Lateral Wall ◽  
Sleep Apnoea ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Individual Site ◽  
Obstructive Sleep ◽  
The Individual

Abstract Study objectives Acoustic analysis of isolated events and snoring by previous researchers suggests a correlation between individual acoustic features and individual site of collapse events. In this study, we hypothesised that multi-parameter evaluation of snore sounds during natural sleep would provide a robust prediction of the predominant site of airway collapse. Methods The audio signals of 58 OSA patients were recorded simultaneously with full night polysomnography. The site of collapse was determined by manual analysis of the shape of the airflow signal during hypopnoea events and corresponding audio signal segments containing snore were manually extracted and processed. Machine learning algorithms were developed to automatically annotate the site of collapse of each hypopnoea event into three classes (lateral wall, palate and tongue-base). The predominant site of collapse for a sleep period was determined from the individual hypopnoea annotations and compared to the manually determined annotations. This was a retrospective study that used cross-validation to estimate performance. Results Cluster analysis showed that the data fits well in two clusters with a mean silhouette coefficient of 0.79 and an accuracy of 68% for classifying tongue/non-tongue collapse. A classification model using linear discriminants achieved an overall accuracy of 81% for discriminating tongue/non-tongue predominant site of collapse and accuracy of 64% for all site of collapse classes. Conclusions Our results reveal that the snore signal during hypopnoea can provide information regarding the predominant site of collapse in the upper airway. Therefore, the audio signal recorded during sleep could potentially be used as a new tool in identifying the predominant site of collapse and consequently improving the treatment selection and outcome.

scholarly journals Zebra finches are sensitive to prosodic features of human speech

2014 ◽  
Vol 281 (1787) ◽  
pp. 20140480 ◽  
Author(s):  
Michelle J. Spierings ◽  
Carel ten Cate
Keyword(s):  
Speech Perception ◽  
Emotional State ◽  
The Other ◽  
Zebra Finches ◽  
Prosodic Features ◽  
Human Speech ◽  
Prosodic Cues ◽  
Paralinguistic Information ◽  
Final Syllable ◽  
Human Specific

Variation in pitch, amplitude and rhythm adds crucial paralinguistic information to human speech. Such prosodic cues can reveal information about the meaning or emphasis of a sentence or the emotional state of the speaker. To examine the hypothesis that sensitivity to prosodic cues is language independent and not human specific, we tested prosody perception in a controlled experiment with zebra finches. Using a go/no-go procedure, subjects were trained to discriminate between speech syllables arranged in XYXY patterns with prosodic stress on the first syllable and XXYY patterns with prosodic stress on the final syllable. To systematically determine the salience of the various prosodic cues (pitch, duration and amplitude) to the zebra finches, they were subjected to five tests with different combinations of these cues. The zebra finches generalized the prosodic pattern to sequences that consisted of new syllables and used prosodic features over structural ones to discriminate between stimuli. This strong sensitivity to the prosodic pattern was maintained when only a single prosodic cue was available. The change in pitch was treated as more salient than changes in the other prosodic features. These results show that zebra finches are sensitive to the same prosodic cues known to affect human speech perception.

scholarly journals False Positive RFID Detection Using Classification Models

2019 ◽  
Vol 9 (6) ◽  
pp. 1154 ◽  
Author(s):  
Ganjar Alfian ◽  
Muhammad Syafrudin ◽  
Bohan Yoon ◽  
Jongtae Rhee
Keyword(s):  
Machine Learning ◽  
Supply Chain ◽  
Real Time ◽  
Outlier Detection ◽  
Radio Frequency Identification ◽  
False Positives ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Automated Identification ◽  
Rfid Data

Radio frequency identification (RFID) is an automated identification technology that can be utilized to monitor product movements within a supply chain in real-time. However, one problem that occurs during RFID data capturing is false positives (i.e., tags that are accidentally detected by the reader but not of interest to the business process). This paper investigates using machine learning algorithms to filter false positives. Raw RFID data were collected based on various tagged product movements, and statistical features were extracted from the received signal strength derived from the raw RFID data. Abnormal RFID data or outliers may arise in real cases. Therefore, we utilized outlier detection models to remove outlier data. The experiment results showed that machine learning-based models successfully classified RFID readings with high accuracy, and integrating outlier detection with machine learning models improved classification accuracy. We demonstrated the proposed classification model could be applied to real-time monitoring, ensuring false positives were filtered and hence not stored in the database. The proposed model is expected to improve warehouse management systems by monitoring delivered products to other supply chain partners.

scholarly journals Acoustic feature-based sentiment analysis of call center data

2017 ◽  
Author(s):  
◽  
Zeshan Peng
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Emotion Recognition ◽  
Sentiment Analysis ◽  
Call Center ◽  
Machine Learning Algorithms ◽  
Language Recognition ◽  
Acoustic Features ◽  
Learning Methods ◽  
Machine Learning Methods

With the advancement of machine learning methods, audio sentiment analysis has become an active research area in recent years. For example, business organizations are interested in persuasion tactics from vocal cues and acoustic measures in speech. A typical approach is to find a set of acoustic features from audio data that can indicate or predict a customer's attitude, opinion, or emotion state. For audio signals, acoustic features have been widely used in many machine learning applications, such as music classification, language recognition, emotion recognition, and so on. For emotion recognition, previous work shows that pitch and speech rate features are important features. This thesis work focuses on determining sentiment from call center audio records, each containing a conversation between a sales representative and a customer. The sentiment of an audio record is considered positive if the conversation ended with an appointment being made, and is negative otherwise. In this project, a data processing and machine learning pipeline for this problem has been developed. It consists of three major steps: 1) an audio record is split into segments by speaker turns; 2) acoustic features are extracted from each segment; and 3) classification models are trained on the acoustic features to predict sentiment. Different set of features have been used and different machine learning methods, including classical machine learning algorithms and deep neural networks, have been implemented in the pipeline. In our deep neural network method, the feature vectors of audio segments are stacked in temporal order into a feature matrix, which is fed into deep convolution neural networks as input. Experimental results based on real data shows that acoustic features, such as Mel frequency cepstral coefficients, timbre and Chroma features, are good indicators for sentiment. Temporal information in an audio record can be captured by deep convolutional neural networks for improved prediction accuracy.

scholarly journals Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Cancers ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 277
Author(s):  
Zuzanna Anna Magnuska ◽  
Benjamin Theek ◽  
Milita Darguzyte ◽  
Moritz Palmowski ◽  
Elmar Stickeler ◽  
...  
Keyword(s):  
Breast Lesion ◽  
Characteristic Curve ◽  
Cancer Diagnostics ◽  
Lesion Detection ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
P Value ◽  
Future Design ◽  
Sensitivity Specificity ◽  
Derivatives Of

Automation of medical data analysis is an important topic in modern cancer diagnostics, aiming at robust and reproducible workflows. Therefore, we used a dataset of breast US images (252 malignant and 253 benign cases) to realize and compare different strategies for CAD support in lesion detection and classification. Eight different datasets (including pre-processed and spatially augmented images) were prepared, and machine learning algorithms (i.e., Viola–Jones; YOLOv3) were trained for lesion detection. The radiomics signature (RS) was derived from detection boxes and compared with RS derived from manually obtained segments. Finally, the classification model was established and evaluated concerning accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve. After training on a dataset including logarithmic derivatives of US images, we found that YOLOv3 obtains better results in breast lesion detection (IoU: 0.544 ± 0.081; LE: 0.171 ± 0.009) than the Viola–Jones framework (IoU: 0.399 ± 0.054; LE: 0.096 ± 0.016). Interestingly, our findings show that the classification model trained with RS derived from detection boxes and the model based on the RS derived from a gold standard manual segmentation are comparable (p-value = 0.071). Thus, deriving radiomics signatures from the detection box is a promising technique for building a breast lesion classification model, and may reduce the need for the lesion segmentation step in the future design of CAD systems.

Sign in / Sign up

Export Citation Format

Share Document