• Nexmo
  • Blog
  • Product
  • Voice
  • Improve the Accuracy of Your Call Transcriptions, Split Recording Now Available in Beta
Split Recording

Improve the Accuracy of Your Call Transcriptions, Split Recording Now Available in Beta

Published April 04, 2018 by Kyle Riordan
Categories:

Way a communication two is street.

Effective communication requires more than just a compilation of words. It requires context, nuance, and most importantly an understanding of who said what and when. Without these considerations, any statement or conversation between two parties can start to resemble the broken gibberish above as opposed to cohesive sentences. Arranged in an errant structure, meanings can be misrepresented, understanding misunderstood, and any insight that otherwise might have been derived from a conversation rendered null and void.

In the abstract, this may seem like a nonsensical scenario but it could easily play itself out if you use basic call recording tools. Whether you are recording a call for the purpose of training new employees, to meet regulatory requirements, or just want a way to retain data to get some more insight on your customers’ needs, understanding who said what within the context of the call is essential to making any of that information actionable.

Calls recorded in mono are just that, mono, singular; there is no way to differentiate who is speaking outside of the unique sound of someone’s voice. The human ear can manage that task but a machine…well, my unflattering monotone can sound just about the same as someone singing soprano.

Enter Split Recording, Exit Audio Ambiguity

Split recording solves this issue by recording participants in stereo. Instead of a single channel, you have two, creating a recording of what a participant hears as well as one of what the participant says. This distinction helps bring clarity to any conversation and can help mitigate the effects of conversations where participants inadvertently—or not so inadvertently—start to speak over one another.

Not only is this easier for a human to understand when they play back the recording, but it is much more clear for a machine. When you plug it into any sort of transcription service, the resulting text will be much more accurate.

The resulting transcriptions are not only more intelligible but also more actionable. Unlike raw audio recordings, transcripts are searchable. So when looking for a word or topic the exercise becomes a simple keyword search as opposed to a drawn-out skimming of the recording listening in for a particular phrase and logging it accordingly.

Getting started with this new feature is easy; all the information you need is in our documentation.

Split Recording Brings Business Benefits

What you can do with this newfound source of information is what makes this tool so powerful. If you are a large marketing organization, you can use it to better analyze your messaging strategies and improve campaign performance. For the large call centers that have to frequently train new employees, this new information can be leveraged to identify means of improving their employee training, clearly highlighting what constitutes a good call in the real world versus one that needs improvement. And if you are an organization that has strict retention requirements you can use this tool to augment your recording and retention capabilities.

Implementing split recording is the step that can move your recording strategy from one of content retention to one that drives actionable insights.

 

Leave a Reply

Your email address will not be published.