Pinned Repositories
Speech-Emotion-Recognition-through-Ensemble-Learning
Emotion recognition can be arduous for machine learning algorithms, especially when a multitude of test samples are input from various people. A way to combat this could be the use of ensemble learning. Ensemble learning allows for a combination of multiple machine learning algorithms to come to the most accurate conclusion based upon multiple predictions. In this paper, we devise a method of emotion recognition using ensemble learning of multiple machine learning algorithms from: k-nearest neighbors (KNN), multilayer perceptron (MLP), and convolutional neural networks (CNN). A combination of these relatively accurate algorithms can establish a versatile model for emotion recognition that classifies a plethora of input data. Using ensemble learning, we were able to create a generalized and accurate model for emotion recognition. Using the collection of emotional speech recordings, following a template like the RAVDESS speech data set. Our hybrid model using ensemble learning was able to achieve accuracy ratings of up to 84.2% on the given data set.
Karplus-StrongGuitarSynthesis-RealTimeDSP
Karplus Strong Real Time Guitar Synthesis through the LaunchPad XL C2000
PoCSD-Project
The goal in the project is to distribute and store data across multiple data servers to: 1) reduce their load (i.e., distributing requests across servers holding replicas), 2) provide increased aggregate capacity, and 3) increase fault tolerance. The redundant block storage should follow the general approach described for RAID-5
Aggregator-Schematics
AggregatorROS
ROS files for 2021-2022 Aggregator
AggregatorTeensy
pico-examples
Pulling out old Pico_W examples
Aggregator-Schematics
bradleyshelley99's Repositories
bradleyshelley99/pico-examples
Pulling out old Pico_W examples
bradleyshelley99/Aggregator-Schematics
bradleyshelley99/Karplus-StrongGuitarSynthesis-RealTimeDSP
Karplus Strong Real Time Guitar Synthesis through the LaunchPad XL C2000
bradleyshelley99/AggregatorTeensy
bradleyshelley99/PoCSD-Project
The goal in the project is to distribute and store data across multiple data servers to: 1) reduce their load (i.e., distributing requests across servers holding replicas), 2) provide increased aggregate capacity, and 3) increase fault tolerance. The redundant block storage should follow the general approach described for RAID-5
bradleyshelley99/AggregatorROS
ROS files for 2021-2022 Aggregator
bradleyshelley99/Speech-Emotion-Recognition-through-Ensemble-Learning
Emotion recognition can be arduous for machine learning algorithms, especially when a multitude of test samples are input from various people. A way to combat this could be the use of ensemble learning. Ensemble learning allows for a combination of multiple machine learning algorithms to come to the most accurate conclusion based upon multiple predictions. In this paper, we devise a method of emotion recognition using ensemble learning of multiple machine learning algorithms from: k-nearest neighbors (KNN), multilayer perceptron (MLP), and convolutional neural networks (CNN). A combination of these relatively accurate algorithms can establish a versatile model for emotion recognition that classifies a plethora of input data. Using ensemble learning, we were able to create a generalized and accurate model for emotion recognition. Using the collection of emotional speech recordings, following a template like the RAVDESS speech data set. Our hybrid model using ensemble learning was able to achieve accuracy ratings of up to 84.2% on the given data set.