System and Method for Multi-Microphone Automated Clinical Documentation

Abstract

A method, computer program product, and computing system for receiving audio encounter information from a first microphone system, thus defining a first audio stream. Audio encounter information may be received from a second microphone system, thus defining a second audio stream. Speech activity may be detected in one or more portions of the first audio stream, thus defining one or more speech portions of the first audio stream. Speech activity may be detected in one or more portions of the second audio stream, thus defining one or more speech portions of the second audio stream. The first audio stream and the second audio stream may be aligned based upon, at least in part, the one or more speech portions of the first audio stream and the one or more speech portions of the second audio stream.

Description

RELATED APPLICATION(S)[0001]This application claims the benefit of the following U.S. Provisional Application No. 63 / 022,269 filed on 8 May 2020, the contents of which are all incorporated herein by reference.BACKGROUND[0002]Automated Clinical Documentation (ACD) may be used, e.g., to turn transcribed conversational (e.g., physician, patient, and / or other participants such as patient's family members, nurses, physician assistants, etc.) speech into formatted (e.g., medical) reports. Such reports may be reviewed, e.g., to assure accuracy of the reports by the physician, scribe, etc.[0003]The process of capturing speech may include distant conversation automated speech recognition (DCASR). DCASR includes multiple microphone systems configured to record and recognize speech of one or more speakers (e.g., a microphone array and a single mobile microphone carried by a speaker). Conventional approaches to DCASR are subject to various challenges. For example, signal acquisition via a numbe...

AI Technical Summary

Benefits of technology

The patent describes a method for aligning and processing audio streams from two microphone systems. The first microphone system may have a microphone array, while the second microphone system may be a mobile electronic device. The method involves detecting speech activity in the audio streams and aligning them based on the detected speech activity. The alignment can be done by weighting the audio streams based on signal-to-noise ratios. The method can also involve processing the aligned audio streams with speech processing systems and combining the outputs to create a single speech processing output. The technical effect of this patent is improved speech processing and better alignment of audio streams from multiple microphone systems.

Problems solved by technology

Conventional approaches to DCASR are subject to various challenges.

For example, signal acquisition via a number of microphone systems (e.g., one or more microphone arrays and one or more mobile microphones) may be problematic.

For example, when beamforming with single microphones, there are single channel noise reduction and de-reverberation methods that cannot be applied to multiple microphone systems.

Additionally, conventional approaches to DCASR are unable to manage the combination of enhanced signals from various devices in a room.

Conventional approaches to DCASR may encounter issues when locating where the speakers are at any given time, tracking their movements, and then identifying their identify.

This may result in less accurate text transcriptions of recorded speech.

In addition, an automated speech recognition (ASR) system, that converts the audio to text, may be unable to process the various metadata and audio signals from multiple sources (e.g., multiple microphone systems).

Images