[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121142-en":3,"doc-seo-121142-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121142,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Analyzing Cricket Songs with Machine Learning - An Undergraduate Research Scholars Thesis","Given recordings of cricket songs, the thesis applies machine learning and audio signal processing to uncover relationships within genera and within species, and to build models that classify songs into the correct genus and species. Audio noise is reduced with a high-pass filter, and songs are represented using mel spectrograms, mel frequency cepstrum coefficients, and magnitude power spectrums. Dimensionality reduction enables visualization of clustering patterns in 2D, supporting high-accuracy genus classification model development and evaluation.","ANALYZING CRICKET SONGS WITH MACHINE LEARNING  \nAn Undergraduate Research Scholars Thesis  \nby  \nRICHARD LIU, LANCE ONDREJ, CHRISTIAN SMITH  \nSubmitted to the LAUNCH: Undergraduate Research office at Texas A&M University  \nin partial fulfillment of requirements for the designation as an  \nUNDERGRADUATE RESEARCH SCHOLAR  \nApproved by  \nFaculty Research Advisors: Dr. Yoonsuck Choe  \nDr. Hojun Song  \nMay 2022  \nMajor: Computer Science  \nCopyright © 2022. Richard Liu, Lance Ondrej, Christian Smith.  \nRESEARCH COMPLIANCE CERTIFICATION  \nResearch activities involving the use of human subjects, vertebrate animals, and/or biohazards must be reviewed and approved by the appropriate Texas A&M University regulatory research committee (i.e., IRB, IACUC, IBC) before the activity can commence. This requirement applies to activities conducted at Texas A&M and to activities conducted at non-Texas A&M facilities or institutions. In both cases, students are responsible for working with the relevant Texas A&M research compliance program to ensure and document that all Texas A&M compliance obligations are met before the study begins.  \nWe, Richard Liu, Lance Ondrej, Christian Smith, certify that all research compliance requirements related to this Undergraduate Research Scholars thesis have been addressed with my Research Faculty Advisors prior to the collection of any data used in this final thesis submission.  \nThis project did not require approval from the Texas A&M University Research Compliance & Biosafety office.  \nTABLE OF CONTENTS  \nPage  \nABSTRACT.................................................................................................................................... 4  \nDEDICATION ................................................................................................................................ 7  \nACKNOWLEDGEMENTS ............................................................................................................ 8  \nNOMENCLATURE ....................................................................................................................... 9  \nSECTIONS  \n1. INTRODUCTION .................................................................................................................. 10  \n1.1 How and Why Crickets Sing ...................................................................................... 10  \n1.2 Lack of Cricket Song Machine Learning Research .................................................... 10  \n1.3 Similar Bird Song Classification Projects .................................................................. 10  \n1.4 Machine Learning Concepts Used.............................................................................. 11  \n2. METHODS ............................................................................................................................. 14  \n2.1 Available Data ............................................................................................................ 14  \n2.2 Determining High-Level Relationships Between the Different Cricket Species ....... 15  \n2.3 Developing a Genus Classification Model ................................................................. 20  \n2.4 Developing a Species Classification Model ............................................................... 26  \n3. RESULTS ............................................................................................................................... 31  \n3.1 t-SNE Plots for Our Extracted Audio Features .......................................................... 31  \n3.2 Genus Classification Model Training Results ............................................................ 36  \n3.3 Species Classification Model Training Results .......................................................... 42  \n3.4 Comparison of the LeNet-5 and SCNNB Models ...................................................... 48  \n4. CONCLUSION .........................................................................","cbCaisMLZ5ISfrYC","https://ap.wps.com/l/cbCaisMLZ5ISfrYC","pdf",938195,1,56,"English","en",105,"# Abstract\n# Dedication\n# Acknowledgements\n# Nomenclature\n# 1. Introduction\n## How and Why Crickets Sing\n## Lack of Cricket Song Machine Learning Research\n## Similar Bird Song Classification Projects\n## Machine Learning Concepts Used\n# 2. Methods\n## Available Data\n## Determining High-Level Relationships Between the Different Cricket Species\n## Developing a Genus Classification Model\n## Developing a Species Classification Model\n# 3. Results\n## t-SNE Plots for Our Extracted Audio Features\n## Genus Classification Model Training Results\n## Species Classification Model Training Results\n## Comparison of the LeNet-5 and SCNNB Models\n# 4. Conclusion\n## The Successful Application of Machine Learning to Cricket Songs\n## Achieving More Generalized Genus and Species Classification Models\n## The Surprising Success of Machine Learning on Small Cricket Song Datasets\n## Cricket Song Classification Applications\n## Future Work\n# References","[{\"question\":\"What problem does the thesis address in cricket song analysis?\",\"answer\":\"It uses machine learning and audio processing to discover relationships within genera and within species, and to classify recordings into the correct genus and species.\"},{\"question\":\"How are the cricket songs preprocessed before modeling?\",\"answer\":\"The audio is denoised using a high-pass filter, and each recording is transformed into multiple feature representations such as mel spectrograms, mel frequency cepstrum coefficients, and magnitude power spectrums.\"},{\"question\":\"How do the researchers evaluate and understand relationships among cricket species?\",\"answer\":\"They reduce the dimensionality of extracted audio features to visualize clustering in 2D space, using these patterns to assess similarity within genera and guide classification modeling.\"}]","Analyzing Cricket Songs with Machine Learning - An Undergraduate Research Scholars Thesis | PDF",1785734044,141,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"analyzing-cricket-songs-with-machine-learning-an-undergraduate-research-scholars-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/analyzing-cricket-songs-with-machine-learning-an-undergraduate-research-scholars-thesis/121142/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in cricket song analysis?","Question",{"text":75,"@type":76},"It uses machine learning and audio processing to discover relationships within genera and within species, and to classify recordings into the correct genus and species.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the cricket songs preprocessed before modeling?",{"text":80,"@type":76},"The audio is denoised using a high-pass filter, and each recording is transformed into multiple feature representations such as mel spectrograms, mel frequency cepstrum coefficients, and magnitude power spectrums.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the researchers evaluate and understand relationships among cricket species?",{"text":84,"@type":76},"They reduce the dimensionality of extracted audio features to visualize clustering in 2D space, using these patterns to assess similarity within genera and guide classification modeling.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]