System and method for secure transcription generation

1. A computer-implemented method, executed on a computing device, comprising:

receiving an input speech signal by utilizing one or more of a plurality of discrete audio acquisition devices to form an audio recording beam, thus enabling capturing of the input speech signal produced by an encounter participant as at least one audio acquisition device is directed toward the encounter participant;

generating, via an automated speech recognition (ASR) system, a transcription of the input speech signal;

identifying one or more splitting points between one or more sensitive content portions and one or more non-sensitive content portions from the transcription;

splitting the input speech signal into the one or more sensitive content portions and the one or more non-sensitive content portions utilizing a splitting system based upon, at least in part, the one or more splitting points, thus defining one or more sensitive content signals and one or more non-sensitive content signals;

processing a transcription of the one or more sensitive content signals generated by a first transcriber, thus defining a sensitive content transcription;

processing a transcription of the one or more non-sensitive content signals generated by a second transcriber, thus defining a non-sensitive content transcription;

generating a combined transcription by combining the sensitive content transcription and the non-sensitive content transcription and by utilizing a splitting signal from the splitting system to synchronize the sensitive content transcription and the non-sensitive content transcription when generating the combined transcription;

training a speech processing model based upon, at least in part, the combined transcription and the input speech signal originally containing the one or more sensitive content portions for training data, wherein the combined transcription acts as labeled data for the input speech signal without disclosing all of the input speech signal to either the first transcriber or the second transcriber; and

processing speech input using the trained speech processing model.

2. The computer-implemented method of claim 1 , wherein the one or more sensitive content portions include one or more of:

personally identifiable information (PII); and

protected health information (PHI).

3. The computer-implemented method of claim 1 , further comprising:

modifying one or more properties of the input speech signal to disguise personal identification information within the input speech signal.

4. The computer-implemented method of claim 1 , further comprising:

providing the one or more sensitive content signals to the first transcriber.

5. The computer-implemented method of claim 4 , wherein providing the one or more sensitive content signals to the first transcriber includes providing each respective sensitive content signal of the one or more sensitive content signals to a different transcriber of a plurality of transcribers.

6. The computer-implemented method of claim 4 , further comprising:

providing the one or more non-sensitive content signals to the second transcriber.

7. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:

receiving an input speech signal by utilizing one or more of a plurality of discrete audio acquisition devices to form an audio recording beam, thus enabling capturing of the input speech signal produced by an encounter participant as at least one audio acquisition device is directed toward the encounter participant;

generating, via an automated speech recognition (ASR) system, a transcription of the input speech signal;

identifying one or more splitting points between one or more sensitive content portions and one or more non-sensitive content portions from the transcript;

splitting the input speech signal into the one or more sensitive content portions and the one or more non-sensitive content portions utilizing a splitting system based upon, at least in part, the one or more splitting points, thus defining one or more sensitive content signals and one or more non-sensitive content signals;

processing a transcription of the one or more sensitive content signals generated by a first transcriber, thus defining a sensitive content transcription;

processing a transcription of the one or more non-sensitive content signals generated by a second transcriber, thus defining a non-sensitive content transcription;

generating a combined transcription by combining the sensitive content transcription and the non-sensitive content transcription and by utilizing a splitting signal from the splitting system to synchronize the sensitive content transcription and the non-sensitive content transcription when generating the combined transcription;

training a speech processing model based upon, at least in part, the combined transcription and the input speech signal originally containing the one or more sensitive content portions for training data, wherein the combined transcription acts as labeled data for the input speech signal without disclosing all of the input speech signal to either the first transcriber or the second transcriber; and

processing speech input using the trained speech processing model.

8. The computer program product of claim 7 , wherein the one or more sensitive content portions include one or more of:

personally identifiable information (PII); and

protected health information (PHI).

9. The computer program product of claim 7 , wherein the operations further comprise:

modifying one or more properties of the input speech signal to disguise personal identification information within the input speech signal.

10. The computer program product of claim 7 , wherein the operations further comprise:

providing the one or more sensitive content signals to the first transcriber.

11. The computer program product of claim 10 , wherein providing the one or more sensitive content signals to the first transcriber includes providing each respective sensitive content signal of the one or more sensitive content signals to a different transcriber of a plurality of transcribers.

12. The computer program product of claim 10 , wherein the operations further comprise:

providing the one or more non-sensitive content signals to the second transcriber.

13. A computing system comprising:

a memory; and

a processor configured to receive an input speech signal by utilizing one or more of a plurality of discrete audio acquisition devices to form an audio recording beam, thus enabling capturing of the input speech signal produced by an encounter participant as at least one audio acquisition device is directed toward the encounter participant, wherein the processor is further configured to generate, via an automated speech recognition (ASR) system, a transcription of the input speech signal, wherein the processor is further configured to identify one or more splitting points between one or more sensitive content portions and one or more non-sensitive content portions from the transcription, wherein the processor is further configured to split the input speech signal into the one or more sensitive content portions and the one or more non-sensitive content portions utilizing a splitting system based upon, at least in part, the one or more splitting points, thus defining one or more sensitive content signals and one or more non-sensitive content signals, wherein the processor is further configured to provide the one or more sensitive content signals to a first set of transcribers of a plurality of transcribers, wherein providing the one or more sensitive content signals to the first set of transcribers includes providing each respective sensitive content signal of the one or more sensitive content signals to a different transcriber of the plurality of transcribers, wherein the processor is further configured to provide the one or more non-sensitive content signals to a second set of transcribers, wherein the processor is further configured to process a transcription of the one or more sensitive content signals generated by a first transcriber, thus defining a sensitive content transcription, wherein the processor is further configured to process a transcription of the one or more non-sensitive content signals generated by a second transcriber, thus defining a non-sensitive content transcription, wherein the processor is further configured to generate a combined transcription by combining the sensitive content transcription and the non-sensitive content transcription and by utilizing a splitting signal from the splitting system to synchronize the sensitive content transcription and the non-sensitive content transcription when generating the combined transcription, wherein the processor is further configured to train a speech processing model based upon, at least in part, the combined transcription and the input speech signal originally containing the one or more sensitive content portions for training data, wherein the combined transcription acts as labeled data for the input speech signal without disclosing all of the input speech signal to either the first transcriber or the second transcriber, and wherein the processor is further configured to process speech input using the trained speech processing model.

14. The computing system of claim 13 , wherein the one or more sensitive content portions include one or more of:

personally identifiable information (PII); and

protected health information (PHI).

15. The computing system of claim 13 , wherein the processor is further configured to: modify one or more properties of the input speech signal to disguise personal identification information within the input speech signal.