Challenge of speech anonymization: cannot develop a model which both preserves speech features well but also effectively anonymizes the speech.

Methodology

• Separate content and speech encoders
• Results in highly concentrated + effective speech content, but with very widespread voiceprint

Demo day

• No value add for demo-day winner
• Competition makes you want to prepare more
• “this much budget for an enriching experience”

Mentor Conversations

None yet

Integration

• Integration into soundscape

Hiring

Need help designing a PCB

sample space \(S\) is the set of all possible outcomes of an experiment. It could be continuous or distinct.

equally likely outcomes

Some sample spaces have equally likely outcomes:

• coin flip
• flipping two coins
• rolling a fair die

If we have equally likely outcomes, \(P(outcome)\) = \(\frac{1}{S}\).

If your sample space has equally likely outcomes, the probability is juts counting:

\begin{equation} P(E) = \frac{count(E)}{count(S)} \end{equation}

Whenever you use this tool, you have to think about whether or not your outcomes are equally likely. For instance, the “sum of two dice rolling” is NOT equally likely.

SARS-COV2

1. traditional stain techniques to analyze the epitopes being targeted
2. uses cyro-EM structural analysis to figure structural points of neutralization
3. predict correct antibodies binding to force certain structures to neutralize covid-19
4. analyze mRNA-vax elicited antibodies to see similarity between those that are useful predicted in 3)

Study identified three epitopes: C1520, C1791, C1717, which changes the structure/activity of all three variants of concern as identified using methods above, and are inpervious to the mutation to the main supersite.