Language Model Improvements
Intelligent Voice has leveraged best in class Transformer architectures to improve language performance across all of the supported languages. As well as the general conversational models, Intelligent Voice focuses on improvements in specific domains (such as “Trader” and insurance) and languages (such as Danish), which are traditionally underserved by other providers.
New Translation Feature
Translation of any of the currently supported languages by Intelligent Voice to English is now available, you can produce transcriptions in the natively spoken language and also receive a separate English transcription. Intelligent Voice will be rolling out beta support for other language pairs in early Q4 2023.
Speaker Identification Improvements (Diarization)
Because of the nature of the environments in which Intelligent Voice operates, highly robust noise resistant voice identification is required. Extensive research has allowed Intelligent Voice’s core speaker identification system to identify individuals on “open” lines where human beings have failed, and these same techniques are now incorporated into the 6.1 release.
Additional Key Developments
In addition to these major improvements, Intelligent Voice have introduced a number of smaller enhancements that will add value to you our customers and we are committed to continual iterative development as we continue to bring you cutting edge technology for all your audio, video and chat surveillance needs. Some key developments worth noting are:
If you are looking for a demo of current or new functionality, please contact your usual sales representative or firstname.lastname@example.org.
Existing users can download the new release from their support portal, but please feel free to get in touch with your support representative to talk more about deployment options, or contact email@example.com.