Blog

04/07/2016

Speechmatics release new German language capability, the latest in the rapidly expanding inventory of supported languages

Speechmatics Auto-Auto responds to market demands for new languages. Speechmatics’ recent release of the Auto-Auto framework continues to create exciting new capability for the Speechmatics platform, delivering German to our line-up of new languages. Neil MacDonald, Chief Revenue Officer, commented “German represents the latest in a continuous and accelerating delivery roadmap of language capability. This ...Read more

13/06/2016

Double reason for Spain to celebrate. Speechmatics release Spanish language pack

Congratulations to Spain and Pique for a great start to their Euro2016 campaign. A cause for a double celebration as Speechmatics releases to market our Spanish language pack. Continuing our relentless drive of bringing a new language to market every two weeks, we are pleased to release our Spanish language pack for use in our ...Read more

30/05/2016

Speechmatics releases Australian English in time for England RFU tour down-under

Speechmatics wishes England RFU well for their upcoming Australian tour and announces availability of Australian English language capability in our Speech Recognition service as a show of support for Australian – English relations. With the England RFU tour of Australia about to kick-off, Speechmatics wishes to offer our heartfelt best wishes to Dylan Hartley and ...Read more

04/05/2016

Speechmatics are pleased to announce ground-breaking language creation technology, Auto-Auto

Auto-Auto is a ground-breaking new framework to support the building of languages for use in Automatic Speech Recognition. This technology will enable the rapid creation and continuous improvement of any language or variants of existing languages, to support specific use-cases such as regional dialects, industry domains or accents. Dr Tom Ash, Speech Recognition Director at ...Read more

02/05/2016

Speechmatics unveils Universal Time Alignment system

Speechmatics releases Universal Time Alignment, our language-independent forced-alignment service to match words in text files to their counterparts in audio files, accurately and automatically delivering improved content discoverability, in any language! The R&D team at Speechmatics have used their deep learning expertise to create a highly accurate and automated system for aligning audio to text.  ...Read more

11/04/2016

Speechmatics 3.2.1 Released

Speechmatics is happy to announce the release of its latest update to its transcription service, Speechmatics 3.2.1.  We have upgraded how we represent acronyms and numbers, so you’re more likely to get digits in your transcripts now (this is 2016 after all, not twenty fifteen). ...Read more

30/10/2015

Speechmatics 3.1 Released

Speechmatics is happy to announce the release of its latest update to its transcription service, Speechmatics 3.1. We have upgraded our language models to improve our performance on short utterances and the starts of longer utterances.  We have also localised to en-US / en-GB spellings, so en-GB mode will be in colour, whereas en-US will ...Read more

03/08/2015

Speechmatics 3.0 Released

Speechmatics is happy to announce the release of its latest update to its transcription service, Speechmatics 3.0.  The core engine has been revamped using recent advances in neural net architectures, resulting in better accuracy and faster turnaround. ...Read more

09/06/2015

Speechmatics 2.3 Released

Speechmatics is happy to announce the release of its latest update, Speechmatics 2.3. The update provides general updates as well as increasing stability further, helping improve overall performance and speed. ...Read more

Stay up-to-date


Sign up

Receive the latest news and updates on what Speechmatics are up to.

Sign up

Follow us