Enhancing musical sound during a networked conference

A non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions for:

• determining presence of an occurrence of a first type of content in a first portion of audio data of an audio signal associated with a virtual meeting;
• in response to determining the presence of the occurrence of the first type of content in the first portion of the audio data, setting a state flag to a first state corresponding to a hysteresis wait time interval;
• in response to setting the state flag to the first state, initiating an instance of the hysteresis wait time interval;
• detecting expiration of the instance of the hysteresis wait time interval;
• analyzing audio features of the first portion of the audio data to obtain a probability that the first portion of the audio data includes musical content, wherein the analyzing is performed by an artificial intelligence (AI) based neural network trained on historical audio segments;
• determining, once the instance of the hysteresis wait time interval has expired, that the probability that the first portion of the audio data includes musical content is equal to or above a threshold;
• and
• applying a first set of signal processing parameters to the audio signal comprising:
• disabling noise suppression for the audio signal;
• applying a linear filter to cancel echo for the audio signal;
• and
• disabling gain control for the audio signal;
• and
• encoding the audio signal using a codec designed for music.

A communication system comprising one or more processors configured to perform operations of:

• determining presence of an occurrence of a first type of content in a first portion of audio data of an audio signal associated with a virtual meeting;
• in response to determining the presence of the occurrence of the first type of content in the first portion of the audio data, setting a state flag to a first state corresponding to a hysteresis wait time interval;
• in response to setting the state flag to the first state, initiating an instance of the hysteresis wait time interval;
• detecting expiration of the instance of the hysteresis wait time interval;
• analyzing audio features of the first portion of the audio data to obtain a probability that the first portion of the audio data includes musical content, wherein the analyzing is performed by an artificial intelligence (AI) based neural network trained on historical audio segments;
• determining, once the instance of the hysteresis wait time interval has expired, that the probability that the first portion of the audio data includes musical content is equal to or above a threshold;
• and
• applying a first set of signal processing parameters to the audio signal comprising:
• disabling noise suppression for the audio signal;
• applying a linear filter to cancel echo for the audio signal;
• disabling gain control for the audio signal;
• and
• encoding the audio signal using a codec designed for music.