Mel spectrogram
A mel spectrogram is the time-frequency picture of audio that speech models actually consume — a spectrogram warped to the mel scale, which spaces frequencies the way human hearing does.
Nearly every modern speech model — Whisper included — reads mel spectrograms rather than raw waveforms. The representation compresses what matters perceptually into an image-like input neural networks handle well.
Related terms
Frequently asked
What is Mel spectrogram?
A mel spectrogram is the time-frequency picture of audio that speech models actually consume — a spectrogram warped to the mel scale, which spaces frequencies the way human hearing does.
Why does Mel spectrogram matter?
Nearly every modern speech model — Whisper included — reads mel spectrograms rather than raw waveforms. The representation compresses what matters perceptually into an image-like input neural networks handle well.
What terms are related to Mel spectrogram?
Closely related concepts: MFCC (Mel-frequency cepstral coefficients), Waveform, Frequency — each has its own entry in this glossary.