AI engineering glossary · Generative media multimodal
What is mel spectrogram?
Mel spectrogram: A spectrogram whose frequency axis is warped to the mel scale, which spaces frequencies the way human hearing perceives pitch, giving finer detail at low frequencies. It is the usual input for speech recognition and the usual target for acoustic models in TTS.
Mel spectrogram: an example
Whisper-style models convert 16 kHz audio into an 80-channel mel spectrogram before processing.
Related terms
- Spectrogram
- Mel scale
- MFCC
- Neural vocoder
More Generative media multimodal terms
- MFCC
- Mode collapse
- Multimodal embedding
- Multimodal model
- Negative prompt
- Neural audio codec
- Neural radiance field
- Neural vocoder
Where you learn it
Mel spectrogram is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.