Skip to main content

Module nisqa

Module nisqa 

Source
Expand description

NISQA — non-intrusive speech-quality learned MOS predictor. NeedsWeights.

NISQA (Mittag et al., 2021) is a deep model (CNN + self-attention) trained to predict speech MOS and its sub-dimensions (noisiness, coloration, discontinuity, loudness) from a single degraded clip, no clean reference. As with DNSMOS, the score IS the trained network; there is no principled hand coded formula that yields it.

This function therefore fails closed: without weights it returns AudioError::BackendUnavailable and never fabricates a MOS. Fabricating a learned MOS is forbidden by project rule.

Functions§

nisqa
Predict a NISQA speech-quality MOS for signal.