AI engineering glossary · Generative media multimodal
What is MOS (mean opinion score)?
Mean opinion score (also called MOS): A subjective quality rating of synthesised speech or audio, obtained by asking listeners to rate samples on a 1 to 5 scale and averaging. It is the standard human evaluation for TTS naturalness.
Mean opinion score: an example
20 listeners rate a TTS sample and give an average of 4.2, close to the 4.5 they give real recordings.
Related terms
More Generative media multimodal terms
- Mel spectrogram
- MFCC
- Mode collapse
- Multimodal embedding
- Multimodal model
- Negative prompt
- Neural audio codec
- Neural radiance field
Where you learn it
Mean opinion score is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.