Speech technology provider Loquendo is further increasing its worldwide presence with the announcement that its ASR, speech recognition offering is now available in the Russian language.
In the European market, Russian is a key language as it is the largest native language in the country.
Back in October, Loquendo (News - Alert) also announced the release of their TTS, text-to-speech offering in Russian along with a new voice, Olga.
The company's ASR offering, available in 21 languages, is a speaker-independent, multilingual speech recognition technology. The offering works to 'accurately and reliably' recognize vocabulary, even large-scale vocabulary continuous speech or noisy environments like over a mobile phone, while in the car or while using VoIP.
Included as part of the latest ASR offering, version 7.7, is Feature Normalization which "improves recognition accuracy, even when run-time operating conditions are different from those on which the ASR was trained," as well as a Continuous Recognition Mode that makes it possible for short commands to be recognized separately and an Improved Confidence Score that calculates confidence values and improves the separation between in- and out-of-grammar utterances, so that more robust dialogues can occur.
Loquendo made headlines recently with the announcement that it would sponsor an international master’s degree in Human Language Technology and Interfaces (HLTI) at the University of Trento.
As part of the sponsorship, Loquendo will provide students and staff with access to the latest speech technologies and will offer hands-on training and experience through work placement at Loquendo.
The company also announced it would be sponsoring Masters and PhD Speech Studies for Spain's National Research Council (CSIC).
Organized by the CSIC Speech Lab, the courses will provide students with a number of activities to take part in including a specialized focus on Phonetics and Phonology, which is not a standard qualification among European Postgraduate studies.
For more, be sure to check out the Speech Recognition and Text to Speech channel on TMCnet.
Loquendo Sponsors Speech Technology Courses at University of Trento
Loquendo Releases MRCP Server 7.1 for Windows and Linux
Loquendo Helps Graduates with Speech Technology Studies at CSIC
Talk to Your Windows-Based Media Center with Speaky
The Importance of Emotion in VUI Design
Stefania Viscusi is an assignment editor for TMCnet, covering VoIP, CRM, call center and wireless technologies. To read more of Stefania’s articles, please visit her columnist page.
Edited by Stefania Viscusi