Abstract: According to an embodiment, a method includes receiving audio data and providing the audio data as input to a first machine learning model to produce transcription data. The audio data is provided as input to a second machine learning model to produce speaker separation data, and the transcription data is segmented based on the speaker separation data to produce speaker separated transcription data. A portion of the speaker separated transcription data is provided as input to a third machine learning model to identify personal identifiable information (PII) text in the portion of the speaker separated transcription data, the portion being associated with a speaker from a plurality of speakers. The method also includes replacing the PII text with redaction text in the portion of the speaker separated transcription data and causing display of the transcription data including the redaction text at a user compute device.

Abstract: Natural language processing can analyze language in apparatus, systems, and methods involving audio, including from body camera video footage, which can be transcribed to extract an audio segment from a video track, to identify starting and ending timestamps of voice, to transcribe the at least one audio segment to identify and separate audio of at least a first speaker, and to score the audio of the first speaker to identify interactions of interest. Audio could be analyzed and scored to record verbal performance, respectfulness, wellness, etc. and speakers from the audio can be detected. Evaluations of officer behavior can be labeled by a machine and confirmed by a human reviewer to identify critical events and justification. Voice printing can be used to identify individual speakers and the audio segments can be weighted to identify key phrases. Positive and negative language in an interaction can be identified using natural language processing.