Technologies

Vecsys Research develops speech processing technologies such as core multilingual large vocabulary speech recognizers for voice interfaces or automatic audio indexing applications.

Substantial advances in speech recognition technology have been achieved over the last decade. This core technology, available in multiple languages, serves as the basis for a range of applications such as voice-interactive database access, as well as more demanding tasks such as the transcription of broadcast data. Vecsys Research has speech-to-text systems with vocabulary sizes up to 300K words for many languages including Arabic, Dutch, English, French, Italian, Mandarin, Russian and Spanish.

Large vocabulary continuous speech recognition is a key technology that can be used to enable content-based information access in audio and video documents. 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. Some applications are data mining, news-on-demand, and media monitoring.

Vecsys Research is providing and further developing these technologies for the Quaero program.

Vecsys Research and LIMSI (CNRS) technologies have been ranked first in the French Technolangue ASR benchmark tests (2005 and 2009) and in the Dutch NBEST ASR benchmarks test (2008, PDF).