Abstract: Provided are methods, systems, and computer-storage media for developing machine learning technology that is less susceptible to bias problems. A machine learning model may be developed with reduced error attributed to one or more sensitive features by utilizing a loss adjustment weight to determine an adjusted loss function used to train the model. The loss adjustment weight may be determined based on a count of a feature-label combination of a sensitive feature. The adjusted loss function is determined and configured to use the loss adjustment weight when determining loss during model training, and the output of the adjusted loss function is an adjusted loss. The machine learning model may be trained until the adjusted loss satisfies a loss threshold, indicative of an acceptable level of model inaccuracy. Accordingly, present embodiments can provide use case specific tailoring to improve machine learning systems by removing biases associated with certain data features.

Abstract: The present disclosure relates to processing operations configured to execute a sound visualization application/service that dynamically generates graphical sound indication providing a visualization of sound for content being presented. A visualization of sound data may be generated and rendered from analysis of sound data, occurring in a manner that is independent from the application/service that is being used to present the content. The sound visualization application/service may be implemented as an independent application/service or plugin that works universally to provide graphical sound visualization regardless of whether content was developed to support graphical sound visualization. For example, a sound visualization application/service is implemented that generates and renders sound indication graphically without requiring access to code of displayed content. Rendered sound visualization may be presented concurrently with displayed content.

Abstract: The present disclosure relates to processing operations configured to execute a sound visualization application/service that dynamically generates graphical sound indication providing a visualization of sound for content being presented. A visualization of sound data may be generated and rendered from analysis of sound data, occurring in a manner that is independent from the application/service that is being used to present the content. The sound visualization application/service may be implemented as an independent application/service or plugin that works universally to provide graphical sound visualization regardless of whether content was developed to support graphical sound visualization. For example, a sound visualization application/service is implemented that generates and renders sound indication graphically without requiring access to code of displayed content. Rendered sound visualization may be presented concurrently with displayed content.