Systems and methods for generating a summary of a multi-speaker conversation

A device, comprising:

• one or more processors configured to:
• analyze a transcript, of a conversation, to separate the transcript into:
• a first section of the transcript that corresponds to a first speaker in the conversation, and
• a second section of the transcript that corresponds to a second speaker in the conversation;
• process, based on a set of delimiters included in the transcript, the first section and the second section to form a first speaker transcript associated with the first speaker and a second speaker transcript associated with the second speaker;
• remove first delimiters, of the set of delimiters, and insert first punctuation marks in the first section;
• remove second delimiters, of the set of delimiters, and insert second punctuation marks in the second section;
• determine, based on one or more topic models, a first set of key terms associated with the first speaker transcript and a second set of key terms associated with the second speaker transcript;
• generate, based on a common set of key terms associated with the first set of key terms and the second set of key terms, a first transcript summary of the first speaker transcript and a second transcript summary of the second speaker transcript;
• generate a conversation summary based on the first transcript summary and the second transcript summary;
• and
• perform an action associated with the conversation summary.

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

• one or more instructions that, when executed by one or more processors of a device, cause the device to:
• determine, based on a transcript of a conversation or based on audio data associated with the transcript, a first section of the transcript that corresponds to a first speaker of the conversation and a second section of the transcript that corresponds to a second speaker of the conversation;
• identify and remove a first set of delimiters in the first section;
• identify and remove a second set of delimiters in the second section;
• insert first punctuation marks in the first section;
• insert second punctuation marks in the second section;
• generate a first speaker transcript from the first section and a second speaker transcript from the second section;
• determine, based on a first topic model, a first set of key terms associated with the first speaker transcript;
• determine, based on a second topic model, a second set of key terms associated with the second speaker transcript;
• generate, based on the first set of key terms and the second set of key terms, a first transcript summary of the first speaker transcript and a second transcript summary of the second speaker transcript;
• generate a conversation summary based on the first transcript summary and the second transcript summary;
• and
• perform an action associated with the conversation summary.