Audio customization in streaming environment

A system comprising:

• a memory, the memory containing one or more instructions;
• and
• a processor, the processor communicatively coupled to the memory, the processor, in response to reading the one or more instructions, configured to:
• monitor a live stream of a presenter, the live stream including a video stream and an audio stream that includes speech of the presenter, the live stream attended by an audience that includes one or more audience members;
• transmit, to a multimodal machine learning model, one or more stream content features of the live stream at a first window of time;
• transfer, to the multimodal machine learning model, one or more audience content features of the audience at the first window of time;
• obtain one or more feature results of the first window of time from the multimodal machine learning model, the feature results based on the stream content features and based on the audience content features;
• send, to an auditory machine learning model, the feature results of the first window of time;
• receive a first audio signal from the auditory machine learning model;
• and
• generate, based on the first audio signal, an augmented stream of the first window of time.

A computer program product, the computer program product comprising:

• one or more computer readable storage media;
• and
• program instructions collectively stored on the one or more computer readable storage media, the program instructions configured to:
• monitor a live stream of a presenter, the live stream including a video stream and an audio stream that includes speech of the presenter, the live stream attended by an audience that includes one or more audience members;
• transmit, to a multimodal machine learning model, one or more stream content features of the live stream at a first window of time;
• transfer, to the multimodal machine learning model, one or more audience content features of the audience at the first window of time;
• obtain one or more feature results of the first window of time from the multimodal machine learning model, the feature results based on the stream content features and based on the audience content features, wherein the feature results are based at least in part on the speech of the presenter;
• send, to an auditory machine learning model, the feature results of the first window of time;
• receive a first audio signal from the auditory machine learning model;
• and
• generate, based on the first audio signal, an augmented stream of the first window of time.