Hacker News Reader

>The car would give you FFT images which you could then look at and see how it changes

Good idea, though AI is much better at doing that in 90% of situations. So filter it thru AI first

As darling of data science Andrew Ng said, "90% of machine learning is feature engineering". So you should probably run the STFT spectrograms through machine learning models rather than the raw audio signal. And anyway raw audio is over 41k samples per second so quite low information density compared to some simple and quite common transformations like STFT anyway.

Reply on news.ycombinator.com