Loquendo, a provider of core speech technologies and voice platforms, today launched Loquendo ASR in the Russian language. This follows the release in October of Loquendo TTS in Russian, with the voice of Olga.

Loquendo ASR is speaker-independent, multilingual speech recognition technology that is currently available in 21 languages. The latest version (ASR 7.7) offers many new features, including:

• Feature Normalization – improves recognition accuracy, even when run-time operating conditions are different from those on which the ASR was trained.
• Continuous Recognition Mode – enables the recognition of short, consecutive commands. Each command is recognised as separate, yet the ASR is immediately ready for the next recognition event.
• Improved Confidence Score – a robust algorithm calculates confidence values, improving separation between in-grammar and out-of-grammar utterances, resulting in more robust dialogues.
• Java support – built on C/C++ APIs.

Russian is the largest native language in Europe, and the release of Loquendo ASR in Russian opens many strategic and expanding markets to the company’s partners in Europe, Asia, and beyond.