The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
The energy of a sound in a few dozen mel bands, every 10 ms or so, on a log scale. The usual input to a speech recognizer.
A mel spectrogram adds up the spectrogram's energy inside a few dozen overlapping bands, spaced evenly in mels. Taking the logarithm of each sum turns energy into something like loudness.
Press Next. The shapes are the ones the worked example at the end of part 2 prints.
Sound as numbers: waveforms and spectrograms · A recording as an array of samples, why the sampling rate must be twice the highest pitch, spectrograms and the window trade-off, and the log-mel features a speech model is given. About 40 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
A recording as an array of samples, why the sampling rate must be twice the highest pitch, spectrograms and the window trade-off, and the log-mel features a speech model is given.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write