Methods and systems for transcription of audio data

Inventors

Spitzer-Williams, Noah • Cho, Choongyeun • Crosley, Thomas • GOIST, Zachary • BELLIA, Daniel • Nguyen, Vinh • ALEXANDER-TAYLOR, Chelsea

Assignees

Axon Enterprise Inc

Abstract

Systems, devices, and methods transcribe words recorded in audio data. A computer-generated transcript is provided. The transcript comprises records for each word in the computer-generated transcript. At least one confirmation input is received for each record. The at least one confirmation input modifies a selected record and automatically identifies a next record for receiving a next confirmation input. A sequence of confirmation inputs may rapidly modify and validate each record in a sequence of records in the computer-generated transcript. A validated transcript is generated from the modified records and is provided from an evidence management system.

Core Innovation

The disclosure describes systems and methods for generating a validated transcript from audio data by using a computer-generated transcript data set that includes a plurality of records, where each record corresponds to a respective word detected in the audio data. The audio data is provided for playback while the transcript records are provided for display, and the user provides at least one first confirmation input associated with a first record via a user interface device. After receiving the confirmation input, the system automatically compares the first record to the plurality of records to determine a matching record comprising a second record.

The validated transcript is generated by validating the second record in accordance with the comparison, wherein the validating comprises modifying the second record. The disclosure further describes optional secondary confirmation inputs that allow incremental editing of label information, including creating new records, merging with matching subsequent records, and deleting intervening records in an additive workflow. In the method claim, comparing comprises matching first label information of the first record with first label information of the second record.

The disclosure also describes integration with an evidence management system that provides the validated transcript along with corresponding audio and evidence, and that may update display properties for record presentation. Display properties can be updated based on validation, selection, and audio playback alignment, including embodiments that limit matching ranges based on playback position and input type/sequence. Additional embodiments generate validated transcript data with updated and filtered record information derived from the confirmation workflow.

Claims Coverage

The independent claims provide a computing device and a computer-implemented method architecture with six core inventive features: storing audio and word-record transcript data, displaying word-level records during playback, receiving first user confirmation input for a first record, automatically comparing to determine a matching record, validating by modifying the matching record to generate a validated transcript, and updating a display property in accordance with the modifying.

Overall, the claims cover generating a validated transcript by displaying word-level transcript records during audio playback, receiving user confirmation for a first record, automatically comparing the confirmed record to select a matching record, and validating the matching record by modifying it. The method claim further recites matching first label information and updating a display property, and the disclosure identifies related refinements including limited comparison ranges, retaining computer-generated label information, deleting intervening records, merging records, and adding records when a third record does not match.

Stated Advantages

Documented Applications