[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122659-en":3,"doc-seo-122659-105":29,"detail-sidebar-cat-0-en-105":89},{"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":20,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},122659,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Interacting with Neural Audio Synthesis Models Through Interactive Machine Learning","Recent advances in neural audio synthesis enable real-time audio generation for musical performance, yet working with these models remains difficult because latent space axes do not map reliably to interpretable musical labels and can differ across models. The paper proposes a proof-of-concept method to steer latent audio models using interactive machine learning by linking human performance gestures to the high-dimensional latent space. A regression model is trained from demonstrated actions, enabling ideation, exploration, and performance with efficient, flexible, and immediate control over generative audio.","The 1st International Workshop on Explainable AI for the Arts  \nInteracting with neural audio synthesis models through interactive machine learning  \nGabriel Vigliensoni and Rebecca Fiebrink  \nCreative Computing Institute, University of the Arts London  \nABSTRACT  \nRecent advances in neural audio synthesis have made it possible to generate audio signals in realtime, enabling the use of applications in musical performance. However, exploring and playing with their high-dimensional spaces remains challenging, as the axes do not necessarily correlate to clear musical labels and may vary from model to model. In this paper, we present a proof-ofconcept mechanism for steering latent audio models through interactive machine learning. Our approach involves mapping the human-performance space to the high-dimensional, computergenerated latent space of a neural audio model by utilizing a regressive model learned from a set of demonstrative actions. By implementing this method in ideation, exploration, and sound and music performance we have observed its efficiency, flexibility, and immediacy of control over generative audio processes.  \nGabriel Vigliensoni and Rebecca Fiebrink. 2023. In the 1st International Workshop on Explainable AI for the Arts (XAIxArts) , ACM Creativity and Cognition (C&C) 2023. Online","cbCailEjQguMmqSN","https://ap.wps.com/l/cbCailEjQguMmqSN","pdf",44382,1,"English","en",105,"# Abstract\n## Problem: interpretability and control challenges\n## Method: mapping performance space to latent space\n## Approach: regression model from demonstrations\n## Applications: ideation, exploration, performance\n## Outcomes: efficiency, flexibility, immediacy of control","[{\"question\":\"Why is controlling neural audio synthesis models difficult in practice?\",\"answer\":\"Latent space dimensions do not necessarily correspond to clear musical labels, and they may vary across models, making exploration and control hard.\"},{\"question\":\"What is the core idea of the proposed interaction method?\",\"answer\":\"The method maps the human performance space into the neural audio model’s high-dimensional latent space using interactive machine learning.\"},{\"question\":\"How is the mapping from performance actions to latent control learned?\",\"answer\":\"A regressive model is trained from a set of demonstrative actions, establishing the relationship between gestures and latent-space behavior.\"}]","Interacting with Neural Audio Synthesis Models Through Interactive Machine Learning | PDF",1785812015,3,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"interacting-with-neural-audio-synthesis-models-through-interactive-machine-learning","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":28},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/interacting-with-neural-audio-synthesis-models-through-interactive-machine-learning/122659/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why is controlling neural audio synthesis models difficult in practice?","Question",{"text":73,"@type":74},"Latent space dimensions do not necessarily correspond to clear musical labels, and they may vary across models, making exploration and control hard.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What is the core idea of the proposed interaction method?",{"text":78,"@type":74},"The method maps the human performance space into the neural audio model’s high-dimensional latent space using interactive machine learning.",{"name":80,"@type":71,"acceptedAnswer":81},"How is the mapping from performance actions to latent control learned?",{"text":82,"@type":74},"A regressive model is trained from a set of demonstrative actions, establishing the relationship between gestures and latent-space behavior.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]