To know more about us: Vocapia Research develops leading-edge, multilingual speech processing technologies exploiting AI methods such as machine learning. These technologies enable unlimited vocabulary speech recognition, automatic audio segmentation, language identification, speaker diarization and audio-text synchronization. Vocapia's VoxSigma™ speech-to-text software suite delivers state-of-the-art performance in over 30 languages and dialects for a variety of audio data types, including broadcast data, parliamentary hearings, conference calls, or phone conversations.
The VoxSigma™ software suite is available for on-site licensing and as a web service. Designed for professional users needing to process large quantities of audio and video documents with support for multichannel and multilingual documents. We offer customization services to tailor our solutions to the most demanding use cases.
Speech recognition, also called speech-to-text or voice-to-text conversion is the key technology for enabling content-based information access in audio and video documents. Once automatically processed the linguistic information and metadata in the structured document are available for further downstream processing, providing direct access to relevant portions of audio documents. Among the most common applications of our technology are audio and audiovisual data mining (broadcast and telephone data), speech analytics, media monitoring, media asset management, speech transcription and subtitling.
We provide solutions and expertise for core speech processing technologies in many languages. For example, speech to text transcription is available for the Arabic, Cantonese, Czech, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Italian, Latvian, Lithuanian, Mandarin, Pashto, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Turkish, Ukrainian and Urdu languages, with several others under development. Our language identification module identifies the spoken language from a set of 100 languages and dialects, and clients can create models for their desired language set.
We offer services to adapt, tune or create specific models or systems tailored to exactly match your needs. Tailoring models for your application is the best way to ensure you get the best possible results for your needs and high accuracy is essential to maximize your ROI. In addition to our online speech recognition service, we offer services for batch processing of very large quantities of data such as archives.

Read this to discover some applications which use our technology such as multiligual audio/video indexing, transcription of business conference calls, and real-time solutions for avionics.

Broadcast monitoring & audio visual archive indexing

The VoxSigma speech-to-text software suite offers advanced language technologies including speech recognition, language identification and speaker diarization to convert raw audio data into structured and searchable XML documents, enabling users to quickly access, analyze and filter audio and video documents. Read more

Plenary and meeting transcription and indexing

VoxSigma helps reduce the production time and cost to produce transcripts, minutes and/or summaries of public presentations and meetings such as plenary hearings for national and local institutions. VoxSigma also aligns existing transcriptions with audio files, thus significantly enhancing usability. Read more

Telephone Speech Analytics

Vocapia's speech recognition software and language identification software process telephone data making the recorded calls searchable and analyzable via text-based methods. VoxSigma is used by call management companies and for defense applications. The transcripts are further analyzed and categorized, generating statistics about customer calls. Large vocabulary continuous speech recognition is a key technology for automatic, comprehensive analysis of recorded calls. Read more

Transcription of business conference calls

Vocapia's speech recognition software significantly reduces the cost of transcribing business conference calls. The audio document is converted to a fully annotated XML document including speech and non speech segments, speaker labels, words with time codes, high quality confidence scores, as well as punctuation. Vocapia offers services to adapt, tune or create specific models or systems tailored to exactly match the application needs. Read more

Video Subtitling

While fully automatic processing generally does not deliver high enough quality subtitles, Vocapia's speaker diarization, speech to text transcription and speech-text alignment technologies significantly reduce the effort entailed when closely integrated in the subtitle creation process. Read more

Avionics

In aircraft cockpits, speech recognition software is used to improve command and control and allow analysis of radio communications to assist pilots. Vocapia provides real-time solutions that enable live analysis of interactions between humans or with the cockpit. Suitable for low power embedded systems, our technology can be seamlessly integrated into aeronautical platforms.
Read more