Vocapia Research announces the availability of beta versions of two new
functionalities to its VoxSigma automatic speech-to-text transcription service,
both providing dynamic vocabulary and language model adaptation. The first new
functionality is an on-the-fly document based adaptation and the second, carries
out adaptation to the news on a daily basis.
Automatic on-the-fly adaptation allows the user to provide texts related to the
audio document being processed, what can be considered topic/domain adaptation.
These accompanying texts serve to increase the lexical coverage of the
speech-to-text system and to adapt the language model to the specific domain of
the audio document with the aim of improving the transcription accuracy.
Daily adaptation based on current news events helps ensure that transcription
system vocabulary stays up-to-date, thereby providing better coverage of hot
news items. This daily update improves the transcription accuracy on popular
topics, particularly on named entities, that is person, company/organization and
place names, that have peaky popularity in news data.
Vocapia Research is a French R&D company and software publisher with over
20 years of experience in providing leading edge speech technologies for many
languages, including most major European languages as well as Arabic,
Mandarin, and Russian. The Vocapia Research VoxSigma®
suite uses advanced language technologies such as language identification,
speech recognition, and speaker identification to transform raw audio and
audiovisual data into structured and searchable XML documents. This technology
relies on decades of research at LISN, with which there is a privileged
partnership. Joint systems developed with LISN have achieved top ranks in
national and international challenges on speech-to-text transcription. Located
at the heart of the science innovation cluster of Paris Saclay, France,
Vocapia Research is a leader in developing and adapting AI-based solutions for
both civil and defence applications. These applications include audio and
audiovisual data mining (broadcast and web data, telephone speech), production
of subtitles, OSINT and COMINT, and the analysis of aeronautical
communications (air traffic control, voice command). Readers who wish to get
more information about Vocapia Research are invited to check out the Vocapia
Research website or use the contact information