首页|Researcher at Obuda University Publishes Research in Machine Learning (Optimizin g Speech Emotion Recognition with Deep Learning and Grey Wolf Optimization: A Mu lti-Dataset Approach)
Researcher at Obuda University Publishes Research in Machine Learning (Optimizin g Speech Emotion Recognition with Deep Learning and Grey Wolf Optimization: A Mu lti-Dataset Approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on artificial intelligen ce have been presented. According to news reporting out of Budapest, Hungary, by NewsRx editors, research stated, "Machine learning and speech emotion recogniti on are rapidly evolving fields, significantly impacting human-centered computing ." Our news editors obtained a quote from the research from Obuda University: "Mach ine learning enables computers to learn from data and make predictions, while sp eech emotion recognition allows computers to identify and understand human emoti ons from speech. These technologies contribute to the creation of innovative hum an-computer interaction (HCI) applications. Deep learning algorithms, capable of learning high-level features directly from raw data, have given rise to new emo tion recognition approaches employing models trained on advanced speech represen tations like spectrograms and time-frequency representations. This study introdu ces CNN and LSTM models with GWO optimization, aiming to determine optimal param eters for achieving enhanced accuracy within a specified parameter set." According to the news editors, the research concluded: "The proposed CNN and LST M models with GWO optimization underwent performance testing on four diverse dat asets-RAVDESS, SAVEE, TESS, and EMODB. The results indicated superior performanc e of the models compared to linear and kernelized SVM, with or without GWO optim izers."
NETL
NSTL
