Speechmatics has launched the Real-Time Virtual Appliance that will reportedly improve automatic speech recognition across the industry. The product will be demonstrated at IBC 2017.
Whilst continuous transcription technology has come a long way, current offerings aren’t reportedly versatile enough to perform effectively across a range of criteria.
With the Real-Time Virtual Appliance, users are reportedly able to plug Speechmatics’ new software directly into an audio stream and get instantaneous real-time transcription. Speechmatics’ technology has been built from the ground up, as per an official release, to offer the same capabilities in real-time as it already does in the batch cloud transcription service.
To increase accuracy further, the release states, Speechmatics’ Real-Time Virtual Appliance adjusts words as the context within a sentence becomes clearer. Users can reportedly adjust the balance between delay and accuracy and also use Speechmatics dynamic transcript parameters to achieve, as per the official release, the best accuracy possible to meet their specific needs.
While customers are reportedly able to embed the Speechmatics’ virtual appliance directly into their infrastructure, there is no reliance on the cloud. Data can be delivered, as per the official spokesperson, within their own network at all times, enabling external issues that may affect latency to be minimised, giving businesses full control.