Deepgram Background Noise Privacy Concern

[nickmenendez-saleshood]

Hi Deepgram community,

I am working with an account that has voiced concerns that Deepgram's Speech-to-Text will pick up PII from conversations happening in the background. Does Deepgram have any documentation that I can share that explains how Nova-3's Speech-to-Text streaming avoids this? If not, are there any background noise cancellation/suppression features available?

We have data privacy concerns that other individuals’ personal information may be picked up by the transcription in the absence of background noise suppression.  Would you please advise how to avoid this?

Thank you!

[deepgram-community[bot]]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
_{Consider joining our Discord community for more opportunity to engage with your fellow Deepgram users. You can earn points which can be redeemed for cool stuff by being active in our communities!}

[deepgram-community[bot]]

Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion.

[deepgram-community[bot]]

It looks like we're missing some important information to help debug your issue. Would you mind providing us with the following details in a reply?

• The programming language you are working in (e.g. JavaScript, Python).
• A request ID that triggered your error or issue.

[deepgram-community[bot]]

It is certainly possible that our STT models will pick up background conversation, as is the case with any ASR model. First I'd recommend taking a look at our redaction functionality, which allows you to redact sensitive information and provides controls for what types of entities you wish to redact. Is there anything specific that this customer is concerned about (I.e. PII in transcripts, data retention, compliance)?

We do not support noise cancellation out of the box, but if this is something that you're interested in trying out we'd recommend Krisp.ai here. That said, noise cancellation technology may not be something you want to rely on for ensuring sensitive background speech isn't transcribed -- while it will suppress background noise, there will be cases where louder background speech may not get filtered out. Given that, I'd more strongly recommend the redaction approach here.

This message was sent by nick kaimakis from Deepgram, via our community automation.

[nickmenendez-saleshood]

Thank you for the information @nkaimakis. By any chance, do you have any official documentation that includes information about how noise cancellation may impact transcription quality?

[deepgram-community[bot]]

This blog post written by one of our Applied Engineering leads is a great resource on that. TLDR is that it can definitely have tradeoffs to transcription accuracy, but the technology is getting better and we do have some customers who find success with it, so at the end of the day we recommend testing it on your specific audio.

This message was sent by nick kaimakis from Deepgram, via our community automation.