This past Wednesday, Amber Galvano and colleagues represented UC Berkeley's D-Lab at the OpenAI Forum's "AI Ethics in Action" virtual event, where they discussed their personal trajectory and experience participating in the Data Science for Social Justice workshop.
Gašper Beguš gave a virtual invited hall titled Modeling language from raw speech with GANs” at the CHAI: Chat about AI colloquium at the School of Data Science and AI, Indian Institute of Technology (IIT Guwahati) on September 13, 2023.
Gašper Beguš published a paper titled "Articulation GAN: Unsupervised modeling of articulatory learning" in proceedings of ICASSP 2023 (IEEE International Conference on Acoustics, Speech and Signal Processing) with Alan Zhou, Peter Wu, and Gopala K. Anumanchipalli. The paper is available here.
Video of the presentation scheduled to be given at the conference in Rhodes, Greece on June 9 is available here.
This paper presents a technique to interpret and visualize intermediate layers in generative CNNs trained on raw speech data in an unsupervised manner. We argue that averaging over feature maps after ReLU activation in each transpose convolutional layer yields interpretable time-series data. This technique allows for acoustic analysis of intermediate layers that parallels the acoustic analysis of human speech data: we can extract F0, intensity, duration, formants, and other acoustic properties from intermediate layers in order to test where and how CNNs encode various types of...