ENCO improves enCaption 5 with speech recognition from Speechmatics

The Autonomous Speech Recognition (ASR) solution from Speechmatics has been integrated into the enCaption5 automated transcription and subtitling system. ENCO.

The agreement between both companies will allow professionals in the sector audiovisual, to the content producers and at television networks create “very accurate” transcriptions, adding closed or open captions both to audiovisual content live and pre-recorded, regardless of the speaker's demographic, age, gender, accent, dialect, or location.

Speechmatics develops transcription systems based on the deep learning and in the voice recognition. Their technology is trained with enormous amounts of unlabeled data without the need for human intervention, offering complete understanding of all voices and dramatically reducing AI bias and errors in speech recognition. The fifth generation of enCaption leverages Speechmatics technology based on a cloud native architecture (although it can also be deployed in hybrid or on-premises workflows) and offers additional features such as integration with external vocabulary sources, the input and output of audiovisual signals, the media indexing and search, advanced punctuation marks and the ability to review and edit transcripts with manual adjustments that automatically update the system's word filters to improve future accuracy. All of this is offering to be compatible in 34 different languages.

Ken Frommert, president of ENCO, praises the technology of Speechmatics (“it is the most beautiful of the AI speech-to-text engines available”) and says that the company is “excited to use its latest technology for enCaption5.”