AudioXD: Audio Across Domains
Dates: August 1-2, 2022
Location: University of Pittsburgh, Pittsburgh, PA
AudioXD: Audio Across Domains is a cross-disciplinary meeting of audio data scientists that will give professionals from all audio-related research fields the opportunity to connect, share ideas, and develop collaborations. This first AudioXD meeting is a collaborative effort of the Kitzes Lab at the University of Pittsburgh, the Academic Data Science Alliance (ADSA), and the Berkeley Institute for Data Science (BIDS), with financial support generously provided by ADSA and the Gordon and Betty Moore Foundation. The event will be hosted at the University of Pittsburgh in Pittsburgh, PA, and will be completely in person.
The target audience for our AudioXD meeting is data scientists, including those in methods disciplines (e.g., statistics, computer science, electrical engineering) and application domains (e.g., music, biology, environmental science, engineering, linguistics, psychology, history, sociology, journalism, law) who conduct research using audio data.
The stated goals of this cross-domain meeting are to 1) Create new interpersonal connections between attendees, and to 2) Identify common research themes, needs, and pain points that could form the basis for new research collaborations. To achieve these goals, the program will be split between rapid-fire knowledge sharing (lightning talks highlighting expertise and challenges across disciplines), unstructured networking (discussion sessions to develop connections and partnerships), and small-group ideation sessions for participants to share new cross-disciplinary ideas.
BIDS Alum Justin Kitzes is currently an Assistant Professor in the Department of Biological Sciences at the University of Pittsburgh. At BIDS, he was a data science fellow and a postdoctoral scholar in the Energy and Resources Group, where his research focused on the development and application of quantitative approaches for predicting the effects of land use and climate change on biodiversity. He has a particular interest in constraint-based theory and methods, such as maximum information entropy, and is currently working to apply this approach to predict the structure of ecological networks and community dynamics in time. He leads the development of the open source Python package macroeco, which supports the development of macroecological methods and their application to conservation. He also has a strong interest in education and training and is a core contributor with the group Software Carpentry, where he develops curriculum and teaches scientific computing workshops.