TRAINED GENERATIVE MODEL SPEECH CODING

A method includes receiving sampled audio data corresponding to utterances and training a machine learning (ML) model, using the sampled audio data, to generate a high-fidelity audio stream from a low bitrate input bitstream. The training of the ML model includes de-emphasizing the influence of low-probability distortion events in the sampled audio data on the trained ML model, where the de-emphasizing of the distortion events is achieved by the inclusion of a term in an objective function of the ML model, which term encourages low-variance predictive distributions of a next sample in the sampled audio data, based on previous samples of the audio data.