Auditory Machine Learning Training and Testing Pipeline: AMLTTP v3.0
The purpose of the Two!Ears Auditory Machine Learning Training and Testing Pipeline (AMLTTP) is to build and evaluate models for auditory sound object annotation and assigning attributes to them. The models are obtained by inductive learning from labeled training data. The framework is tightly coupled with the Two!Ears system.
While the pipeline is designed with flexibility in mind and is extendable to new target attributes, data features, or model and training algorithms, it so far serves the specific purpose of training and evaluation of block-based auditory object-type, object-location, and number-of-sources classifiers using data from simulated auditory scenes generated within the same framework.
We recommend always checking at Github whether there is a new version available.