AI engineering glossary · Generative media multimodal
What is MFCC?
MFCC: Mel-frequency cepstral coefficients, a compact set of numbers describing the spectral shape of a short audio frame, computed from a mel filter bank, a logarithm and a discrete cosine transform. They were the standard speech feature before deep learning.
MFCC: an example
Each 25 ms frame of speech is summarised as 13 MFCC values, which a classic recogniser used to tell vowels apart.
Related terms
- Mel spectrogram
- Mel scale
- Automatic speech recognition
More Generative media multimodal terms
- Mode collapse
- Multimodal embedding
- Multimodal model
- Negative prompt
- Neural audio codec
- Neural radiance field
- Neural vocoder
- Noise schedule
Where you learn it
MFCC is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.