Digital Commons Network^™

Deep Learning Based Speech Enhancement And Its Application To Speech Recognition, Ju Lin

All Dissertations

Speech enhancement is the task that aims to improve the quality and the intelligibility of a speech signal that is degraded by ambient noise and room reverberation. Speech enhancement algorithms are used extensively in many audio- and communication systems, including mobile handsets, speech recognition, speaker verification systems and hearing aids. Recently, deep learning has achieved great success in many applications, such as computer vision, nature language processing and speech recognition. Speech enhancement methods have been introduced that use deep-learning techniques, as these techniques are capable of learning complex hierarchical functions using large-scale training data. This dissertation investigates the deep learning …

Using Custom Ner Models To Extract Dod Specific Entities From Contracts, Kayla P. Haberstich

Theses and Dissertations

The Air Force Sustainment Center collected 3.7 million contracts onto the Air Force Research Laboratory’s high power computers. They are in the format of a .pdf or scanned document, making them unstructured data. The Data Analytics Resource Team extracted the documents into a textual format for use in further analysis. This thesis looks to extract four DOD specific entities (NSN, Part Number, CAGE Code, and Supplier Name) from the contracts using custom NER models. This newly extracted information will allow the Air Force to identify what parts are supplied by which vendors. This information along with historical CLIN pricing for …

Assessment Of Visual Field Performance Asymmetries While Utilizing Aircraft Attitude Symbology, George A. Reis

Theses and Dissertations

Two experiments were conducted to examine visual performance asymmetries when perceiving complex, meaningful visual stimuli, such as the Arc Segment Attitude Reference (ASAR). The ASAR symbology represents an aircraft’s attitude. Experiment 1 examined participants’ performance while recalling and reporting various attitudes of ASAR symbology and a Gabor patch, which were briefly presented in the peripheral visual field. Performance was assessed for coordinate and categorical judgments at various display locations. The results were consistent with the horizontal-vertical anisotropy literature, which implies that performance would be better for stimuli placed on the horizontal meridian as compared to stimuli placed on the vertical …

Evolutionary Algorithms For Function Model Synthesis, Amaninder Singh Gill

Theses and Dissertations

Function modelling plays an essential role in the systematic design process. Designers are trained in the academia trained on function models, yet the acceptance of function models in the industry remains sparse. A possible reason is that there is a lack of computational support for synthesizing function models. The research presented in this dissertation aims to fill that gap. A conceptual proof of function model synthesis using a Genetic Algorithm (GA) is initially presented. Thereafter a priori rules to evaluate function model have been developed. These rules do not rely on a designer conveying designer intent to the algorithm, which …

Audio Representations For Deep Learning In Sound Synthesis: A Review, Anastasia Natsiou, Sean O'Leary

Articles

The rise of deep learning algorithms has led many researchers to withdraw from using classic signal processing methods for sound generation. Deep learning models have achieved expressive voice synthesis, realistic sound textures, and musical notes from virtual instruments. However, the most suitable deep learning architecture is still under investigation. The choice of architecture is tightly coupled to the audio representations. A sound’s original waveform can be too dense and rich for deep learning models to deal with efficiently - and complexity increases training time and computational cost. Also, it does not represent sound in the manner in which it is …

A Marine Gis-Based Alert System To Prevent Vessels Collision With Offshore Platforms, Sheng-Long Kao, Ki-Yin Chang, Tai-Wen Hsu

Journal of Marine Science and Technology–Taiwan

How to effectively use an intelligent aid-to-navigation (AtoN) to prevent ships from accidentally colliding with offshore marine platforms (OMPs) is an important issue for maritime environment. This study proposes a novel collision alert system with three components to process Automatic Identification System (AIS) data in the cloud and broadcast AtoNs to ships in order to avoid collision with OMPs. The first component receives as input fuzzy linguistic variables (vessel size, relative speed, and approach distance) from the AIS data and calculates the radius of the guarding ring. The second component serves a Marine GIS (MGIS), where the system simulates the …

Catenate: Creating An Interdisciplinary Art Project, Brian Phillips, Melissa Eddings Mancuso, Emma Sherban

Symposium on Education in Entertainment and Engineering

This paper will present the rationale for, the challenges of, and successes encountered in the formation process of an interdisciplinary Visual & Performing Arts Project, Catenate, at Ohio Northern University’s School of Visual & Performing Arts.

Provenance: An Intermediary-Free Solution For Digital Content Verification, Bilal Yousuf, M. Atif Qureshi, Brendan Spillane, Gary Munnelly, Oisin Carroll, Matthew Runswick, Kirsty Park, Eileen Culloty, Owen Conlan, Jane Suiter

Articles

The threat posed by misinformation and disinformation is one of the defining challenges of the 21st century. Provenance is designed to help combat this threat by warning users when the content they are looking at may be misinformation or disinformation. It is also designed to improve media literacy among its users and ultimately reduce susceptibility to the threat among vulnerable groups within society. The Provenance browser plugin checks the content that users see on the Internet and social media and provides warnings in their browser or social media feed. Unlike similar plugins, which require human experts to provide evaluations and …

Effectiveness Assessment Of The Search-Based Statistical Structural Testing, Yang Shi, Xiaoyu Song, Marek A. Perkowski, Fu Li

Electrical and Computer Engineering Faculty Publications and Presentations

Search-based statistical structural testing (SBSST) is a promising technique that uses automated search to construct input distributions for statistical structural testing. It has been proved that a simple search algorithm, for example, the hill-climber is able to optimize an input distribution. However, due to the noisy fitness estimation of the minimum triggering probability among all cover elements (Tri-Low-Bound), the existing approach does not show a satisfactory efficiency. Constructing input distributions to satisfy the Tri-Low-Bound criterion requires an extensive computation time. Tri-Low-Bound is considered a strong criterion, and it is demonstrated to sustain a high fault-detecting ability. This article tries to …

Higher Sound Levels In K-12 Classrooms Correlate To Lower Math Achievement Scores, Laura Caroline Brill, Lily M. Wang

Durham School of Architectural Engineering and Construction: Faculty Publications

Sound levels from occupied classrooms have been gathered from 220 classrooms across four grade levels (3, 5, 8 and 11) over six school days each and processed with k-means clustering into speech and non-speech clusters. Three metrics describing the classroom acoustics, including the average daily A-weighted equivalent level for non-speech, the average daily difference between the A-weighted equivalent levels for speech and nonspeech (a signal to noise ratio), and the mid-frequency averaged reverberation time, were analyzed against classroom-aggregated standardized reading and math achievement test scores, while controlling for classroom demographics including socioeconomic status. Interactions between the metrics and demographics were …

Inventory Control Using Fuzzy Inference System And Adaptive Neuro Fuzzy Inference System Under Uncertain Conditions, Ali Abdulmajeed Ali, Arzaq Mohammed Ali Kulaib

Hadhramout University Journal of Natural & Applied Sciences

Supply chain management plays a significant role for running business efficiently, as it integrates management of materials and information flows between supply chain parties Fuzzy Inference System (FIS) and Adaptive Neuro Fuzzy inference system (ANFIS) are expert systems widely used to deal with imprecise and vague data. In this paper FIS and ANFIS are implemented to deal with the uncertainty regarding demand, lead time and inventory level in continuous inventory control system in order to obtain the optimal order quantity and reorder point. These two models are compared with Economic Order Quantity (EOQ) model at the different service level to …

Formulating Automated Responses To Cognitive Distortions For Cbt Interactions, Ignacio De Toledo, Giancarlo Salton, Robert J. Ross

Conference papers

One of the key ideas of Cognitive Behavioural Therapy (CBT) is the ability to convert negative or distorted thoughts into more realistic alternatives. Although modern machine learning techniques can be successfully applied to a variety of Natural Language Processing tasks, including Cognitive Behavioural Therapy, the lack of a publicly available dataset makes supervised training difficult for tasks such as reforming distorted thoughts. In this research, we constructed a small CBT dataset via crowd-sourcing, and leveraged state of the art pre-trained architectures to transform cognitive distortions, producing text that is relevant and more positive than the original negative thoughts. In particular, …

Control System Synthesis With Self-Adapting Regulator By Interactive Adaptation Method, Isamiddin Xakimovich Siddikov, Renata Nikolayevna Izmaylova

Chemical Technology, Control and Management

The research results on the creation of a self-adapting control system for a nonlinear dynamic object based on the theory of intelligent control using interactive adaptation methods have been presented. The lack of an accurate description and the nonlinearity of the dynamic properties of the object under study, the presence of mutual influence of cross communication channels in the control circuits, as well as the influence of various types of uncertainties associated with the lack of a priori information about the process, significantly complicate the solution of the problem of synthesis of highly efficient control systems for dynamic objects, which …

Incorporating Virtual Reality Training In An Introductory Public Speaking Course, Kevin Kryston, Henry Goble, Allison Eden

Journal of Communication Pedagogy

This study presents the results of two studies using a virtual reality (VR) public-speaking training simulation as an instructional aid in a basic communication course. Results from the first study suggest that VR practice was associated with higher subsequent speech delivery grades in the course compared to no practice. However, VR practice did not reduce public speaking anxiety (PSA). In a follow-up study, VR practice was compared with other forms of lab-based practice including in front of a mirror and a recorded video session. All forms of lab practice (VR, mirror, or video) were associated with higher speech grades than …

A Critical Perspective On The Indian Experience, K. P. Madhu

Online Journal of Space Communication

Growth in the use of satellites for education has been phenomenal in India. Beginning in the 1970s with the SITE project (Satellite Instructional Television Experiment) using a borrowed US satellite, then in the 1980s having its own indigenous INSAT satellite for educational TV, to having a full fledged educational channel on national TV in the 1990s, to the potential of 72 educational channels on EDUSAT at the beginning of the 21st century, shows long-term interest and commitment to this sector.

The Emily Dickinson Machine & Hybrid Poetry Generation, Juliana Shihadeh

Computer Science and Engineering Master's Theses

This thesis introduces EMILY, a machine that creates original poems in the style of renowned poet Emily Dickinson. Dickinson’s succinct and syntactically distinct style with unconventional punctuation makes for an interesting challenge for automated poetry creation. Furthermore, we adapt EMILY to answer the following hypothetical question: What if Emily Dickinson had collaborated with another poet from a different time period? To this end, we introduce Hybrid Generative Poetry, which simultaneously integrates poetic elements from multiple poets. Using two distinct approaches to Hybrid Poetry generation, we create poetry in the combined styles of Emily Dickinson and Robert Frost. User studies are …

Problems Of Modeling And Control Of The Technological Process Of Ore Grinding, Djalolitdin Pakhritdinovich Mukhitdinov, Sanjar Boybutayev

Chemical Technology, Control and Management

The article analyzes the methods of mathematical modeling of the closed-loop process of fine grinding of ore in order to predict the composition of the crushed raw material. Analyzed modeling methods that consider the control of classification of crushed raw materials and finished products by the size of the recirculating load, simulation modeling methods, methods that use neuro-phase netthe research apparatus, in which the fuzzy logic apparatus serves as a fundamental component for the formation of conclusions. The materials presented in the article reflect the theoretical substantiation and generalization of the accumulated practical experience in modeling and control of the …

Construction Disputes And Associated Contractual Knowledge Discovery Using Unstructured Text-Heavy Data: Legal Cases In The United Kingdom, Jeehee Lee, Youngjib Ham, June-Seong Yi

Civil and Environmental Engineering and Construction Faculty Research

Construction disputes are one of the main challenges to successful construction projects. Most construction parties experience claims—and even worse, disputes—which are costly and time-consuming to resolve. Lessons learned from past failure cases can help reduce potential future risk factors that likely lead to disputes. In particular, case law, which has been accumulated from the past, is valuable information, providing useful insights to prepare for future disputes. However, few efforts have been made to discover legal knowledge using a large scale of case laws in the construction field. The aim of this paper is to enhance understanding of the multifaceted legal …

Using Artificial Neural Network And Fuzzy Inference System Based Prediction To Improve Failure Mode And Effects Analysis: A Case Study Of The Busbars Production, Saeed Na’Amnh, Muath Bani Salim, István Husti, Miklós Daróczi

Mechanical Engineering Faculty Publications and Presentations

Nowadays, Busbars have been extensively used in electrical vehicle industry. Therefore, improving the risk assessment for the production could help to screen the associated failure and take necessary actions to minimize the risk. In this research, a fuzzy inference system (FIS) and artificial neural network (ANN) were used to avoid the shortcomings of the classical method by creating new models for risk assessment with higher accuracy. A dataset includes 58 samples are used to create the models. Mamdani fuzzy model and ANN model were developed using MATLAB software. The results showed that the proposed models give a higher level of …

The “East Side” Of Las Vegas: A Latinx Historical Framework, Nathalie Martinez

Spectra Undergraduate Research Journal

Spanish heritage speakers in the United States are a reflection of everchanging linguistic and sociolinguistic pressures that result in myriad varieties across generations. This paper provides a preliminary historical framework to fill this gap of linguistic knowledge in the Spanish-speaking community of Las Vegas, Nevada. The goals were two-fold: (1) highlight the largest Spanish-speaking communities in Las Vegas and (2) explore the significance of the East Side in the history of the Latinx population of Las Vegas. Through the analysis of oral histories and historical works, the investigation highlights the Mexican, Salvadoran, and Cuban populations of Las Vegas and their …

Ronald E. Mcnair Scholars Program Profiles And Abstracts 2021, Mcnair Scholars Program

McNair Symposium

This is the complete event program and provides presentation abstracts and biographies of McNair scholars and their mentors.

An Automated Method To Enrich Consumer Health Vocabularies Using Glove Word Embeddings And An Auxiliary Lexical Resource, Mohammed Ibrahim, Susan Gauch, Omar Salman, Mohammed Alqahtani

Computer Science and Computer Engineering Faculty Publications and Presentations

Background

Clear language makes communication easier between any two parties. A layman may have difficulty communicating with a professional due to not understanding the specialized terms common to the domain. In healthcare, it is rare to find a layman knowledgeable in medical terminology which can lead to poor understanding of their condition and/or treatment. To bridge this gap, several professional vocabularies and ontologies have been created to map laymen medical terms to professional medical terms and vice versa.

Objective

Many of the presented vocabularies are built manually or semi-automatically requiring large investments of time and human effort and consequently the …

Finding Bert’S Idiomatic Key, Vasudevan Nedumpozhimana, John Kelleher

Conference papers

Sentence embeddings encode information relating to the usage of idioms in a sentence. This paper reports a set of experiments that combine a probing methodology with input masking to analyse where in a sentence this idiomatic information is taken from, and what form it takes. Our results indicate that BERT’s idiomatic key is primarily found within an idiomatic expression, but also draws on information from the surrounding context. Also, BERT can distinguish between the disruption in a sentence caused by words missing and the incongruity caused by idiomatic usage.

Language As A Factor In Aviation Accidents And Serious Incidents: A Handbook For Accident Investigators Ed. 2, Elizabeth Mathews, Anthony T. Brickhouse, Joan Carson Ph.D., Enrique Valdes

Handbooks

The purpose of this handbook is to support accident investigators in the identification and consideration of possible language factors in aviation accidents and serious incidents. This handbook provides guidance, background information, and tools that will assist accident investigators in conducting a systematic review of possible language factors.

Evaluation Of Patient Experience Using Natural Language Processing Algorithms, Sofia Veronica Ortega

Open Access Theses & Dissertations

INTRODUCTION: Healthcare organizations are making extensive efforts to improve the patient experience. Enhancing patient/client experience and outcomes is crucial for patient-centered care and can reveal improvement opportunities. Healthcare settings currently rely on surveys (e.g., HCAHPS) and patient feedback to measure patient experience. Studies have identified that utilizing patient journey mapping can better capture patient experience throughout all stages of the patient's journey and provide quality and process improvement recommendations at specific hotspots. However, these measurement techniques are time-consuming and resource intensive. AIM: This research aims to measure patient experience of breast cancer patients from social media data using natural language …

Evaluating Decision Making In Sustainable Project Selection Between Literature And Practice, Rakan Alyamani, Suzanna Long, Mohammad Nurunnabi

Engineering Management and Systems Engineering Faculty Research & Creative Works

A robust project selection process is critical for the selection of sustainable projects that meet the needs of an organization or community. There are multiple factors or criteria that can be considered in the selection of the appropriate sustainable project, but it can be challenging to find sufficient depth of expert opinion to perform a strong evaluation of these criteria. Several researchers have turned to the sustainable project literature as a source of expert opinion to evaluate the criteria used in sustainable project selection and rank them based on importance using different multi-criteria decision-making (MCDM) methodologies. However, using the literature …

Estimating Homophily In Social Networks Using Dyadic Predictions, George Berry, Antonio Sirianni, Ingmar Weber, Jisun An, Michael Macy

Research Collection School Of Computing and Information Systems

Predictions of node categories are commonly used to estimate homophily and other relational properties in networks. However, little is known about the validity of using predictions for this task. We show that estimating homophily in a network is a problem of predicting categories of dyads (edges) in the graph. Homophily estimates are unbiased when predictions of dyad categories are unbiased. Node-level prediction models, such as the use of names to classify ethnicity or gender, do not generally produce unbiased predictions of dyad categories and therefore produce biased homophily estimates. Bias comes from three sources: sampling bias, correlation between model errors …

Spanish And English Phoneme Recognition By Training On Simulated Classroom Audio Recordings Of Collaborative Learning Environments, Mario J. Esparza Perez

Electrical and Computer Engineering ETDs

Audio recordings of collaborative learning environments contain a constant presence of cross-talk and background noise. Dynamic speech recognition between Spanish and English is required in these environments. To eliminate the standard requirement of large-scale ground truth, the thesis develops a simulated dataset by transforming audio transcriptions into phonemes and using 3D speaker geometry and data augmentation to generate an acoustic simulation of Spanish and English speech. The thesis develops a low-complexity neural network for recognizing Spanish and English phonemes (available at github.com/muelitas/keywordRec). When trained on 41 English phonemes, 0.099 PER is achieved on Speech Commands. When trained on 36 Spanish …

A Configurable Mining Approach For Learning Services Customization, Aya M. Mostafa Amm, Yehia M. Helmy Ymh, Amira M. Idrees Ami

Future Computing and Informatics Journal

There is no doubt that this age is the age of data and technology. Moreover, there is tremendous development in all fields. The personalized material is a good approach in the different fields. It provides a fit material that matches the styles of readers. It supports readers in various reading domains. This research paper aims to support students in the educational system. Additionally, the research paper designs to increase education values for students. Furthermore, the research paper builds the smart appropriate materials through Egyptian Knowledge Banking (EKB) based on the learner question. The Egyptian Knowledge Bank (EKB) is a rich …

Indonesian Sentence Boundary Detection Using Deep Learning Approaches, Joan Santoso, Esther Irawati Setiawan, Christian Nathaniel Purwanto, Fachrul Kurniawan

Knowledge Engineering and Data Science

Detecting the sentence boundary is one of the crucial pre-processing steps in natural language processing. It can define the boundary of a sentence since the border between a sentence, and another sentence might be ambiguous. Because there are multiple separators and dynamic sentence patterns, using a full stop at the end of a sentence is sometimes inappropriate. This research uses a deep learning approach to split each sentence from an Indonesian news document. Hence, there is no need to define any handcrafted features or rules. In Part of Speech Tagging and Named Entity Recognition, we use sequence labeling to determine …