LAb41 discusses next steps on their VOiCES project.
Advanced Data Analytics
LAb41 discusses VOiCES, the first open source speech data-set recorded in real environments with far-field microphones, capturing reverberant acoustics and background noise.
Lab41 recently started tackling the question of how much information is a model memorizing and how can we better understand this?
Machine Learning (ML) models are increasingly becoming more ubiquitous in our everyday lives, many of the models built using personal and sensitive data. For instance, ML models now regularly use unique biometric data to identify us, such as our voices, our fingerprints, faces or iris’.
Last year, we announced the creation of Squiggle, an algorithm for intuitive DNA sequence visualization and analysis along with an accompanying software package to enable interactive exploration of DNA sequences. Next, we created DNAvisualization.org so that it requires only a web browser to operate.
Discusses the VOiCES project and removal of dynamic noise, sources of noise which do not repeat, or do so only sporadically.