3. FORENSIC SCIENCES
» Forensic technologies
6. INFORMATION & COMMUNICATION TECHNOLOGIES
» Intelligence systems
» Software, Data Processing
Core competencies
Founded in 2000, Vocapia Research is an R&D company specialized in the development of multilingual technologies for speech and
language processing, in particular speech to text transcription systems, audio and speaker segmentation and identification, and
language recognition. It has privileged partnerships with the LIMSI (CNRS) laboratory.
Statistical methods are used in the VoxSigma software suite to model spoken language and to build leading edge speech processing
technologies which can serve a variety of applications, in particular
broadcast monitoring, audio visual archive indexing, debate and lecture transcription and indexing, telephone speech analytics,
transcription of business conference calls, and video subtitling. Large vocabulary continuous speech recognition is a key technology
that can be used to enable content-based information access in audio and video documents since most of the linguistic information is
encoded in the audio channel of audiovisual data, which once transcribed can be accessed using text-based tools. Via language
identification, speech recognition, and speaker recognition, spoken document retrieval can support random access using specific
criteria to relevant portions of audio documents, reducing the time needed to identify recordings in large multimedia databases. Vocapia
Researchs VoxSigma speech-to-text systems include many languages: Arabic, Dutch, English, Finnish, French, German, Greek,
Hungarian, Italian, Latvian, Lithuanian, Mandarin, Polish, Portuguese (European and Brazilian), Romanian, Russian, Spanish, Swedish
and Turkish.
The VoxSigma software suite provides large vocabulary speech recognition capabilities in multiple languages, as well as audio
segmentation and partitioning, speaker identification and language recognition. The software suite has been designed for professional
users needing to transcribe large quantities of audio and video documents such as broadcast data, either in batch mode or in real-time.
Versions specifically target the transcription of conversational telephone speech and call-center data. VoxSigma is also available as a
Web service. The VoxSigma SaaS offers full speech transcription, audio indexing and speech-text alignment capabilities via a REST
API over HTTPS .