[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-35823":3,"doc-seo-35823":29},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},35823,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Unveiling Hidden Factors Explainable AI for Feature Boosting in Speech Emotion Recognition","Speech emotion recognition (SER) is applied across mental health, education, and human-computer interaction, yet suffers from accuracy loss due to high-dimensional feature sets containing irrelevant and redundant information. The study introduces an iterative feature boosting method that combines careful feature selection with explainability. A feature evaluation loop using Shapley values refines feature subsets to improve performance while maintaining transparency. Experiments on TESS, EMO-DB, RAVDESS, and SAVEE outperform state of the art and identify crucial emotion features.","","cbCaicqJF2BZQPMp","https://ap.wps.com/l/cbCaicqJF2BZQPMp","pdf",3683149,1,24,"English","en",105,"# Abstract\n# Method: Iterative feature boosting with explainable feature evaluation\n# Experimental validation on SER benchmarks\n# Key contributions and advantages","[{\"question\":\"What problem does the proposed approach address in speech emotion recognition (SER)?\",\"answer\":\"SER accuracy is hindered by high-dimensional feature sets that include irrelevant and redundant information. The approach targets this by selecting and refining features toward greater relevance and usefulness.\"},{\"question\":\"How does the method incorporate explainability into feature boosting?\",\"answer\":\"It uses a feature evaluation loop based on Shapley values. Iteratively re-fined feature sets balance improved model performance with transparent, explainable predictions.\"},{\"question\":\"On which datasets and how does the approach perform compared with existing methods?\",\"answer\":\"The method is validated on TESS, EMO-DB, RAVDESS, and SAVEE. Results outperform state-of-the-art methods and support identifying critical features for emotion determination.\"}]",1782594670,60,null]