Release 1.8.2: Multi-channel recordings

February 2024 |
last updated on 27. March 2024

The 1.8.2 release of GoSpeech offers enhanced functionality, including support for multi-channel recordings and improved recognition results. It also enables our enterprise customers to process very long recordings.

 

Multichannel recordings

Multi-channel recordings are recordings that simultaneously record several audio signals from different sources or channels. Typically, these are different microphones.


Such recordings are often made in large meeting rooms or during music or film productions. To create multi-channel recordings, you need special hardware components. A simple example: microphones or other audio sources send sound information via cable to an audio interface that can process multiple channels. From there, the data is transferred to the recording software on the computer.
 

Why does GoSpeech support multi-channel recording?

GoSpeech's AI-based speaker separation already works very well. However, the already separated audio tracks of individual speakers and the improved sound quality mean that even more precise speaker assignments and even better recognition results can be achieved.

 

What should I pay attention to when using the 'Multi-channel recording' function?

Make sure that the individual audio tracks do not record the conversations of other participants, as this can affect the recognition results.

The following graphic illustrates the recognition result when the microphones record other participants in the room:

 

Make sure that all microphones are synchronized to ensure that the recorded audio data is timed. This is crucial so that the data from the different channels can be combined correctly.

 

Improved detection:

Thanks to a revision of the post-processing procedure, GoSpeech delivers even more precise recognition results in the new version. However, if the representation of the terms does not meet your expectations, please use the 'Suggest another spelling' function to let us know your suggestions for improvement.

 

Extension for enterprise solutions:

With the latest release, our Enterprise solutions can now transcribe files longer than 5 hours. Please note that this function is only available to our business customers. If you are interested in using very long files, please arrange a non-binding consultation with us.

Arrange a non-binding consultation

 

API integration

We are currently working intensively on our GoSpeech API to enable our business customers to integrate GoSpeech into their existing systems via an interface.

Would you like to find out more about the possible applications and functionalities of our API? Then arrange a non-binding initial appointment with our business development team.

Arrange a consultation