Loquendo (News - Alert), global provider of speech recognition (technology), announced a newer version of Loquendo ASR 7.9 and Loquendo TTS 7.20, enabling users to exploit all the new features and benefits offered by those two key new releases.

Loquendo Speech Suite now supports the latest version of the W3C (News - Alert) standard SSML 1.1, enabling the creation of TTS prompts in a standardized, cross-platform and XML-based mark-up language.

The new platform has been enriched with enhanced logging capability to facilitate application development and tuning. On the configuration side, Loquendo Speech Suite inherits the simplified installation procedure of LTTS 7.20 and makes it easier to switch between MRCP v1 and v2 profiles, making it less hassle for users.

Loquendo Speech Suite and Loquendo MRCP Server is the ideal solution for developing large-scale automated telephony applications using Loquendo multilingual speech, and can be configured as TTS-only, ASR-only, or both TTS and ASR.

Both are integrated via MRCP (Media Resource Control Protocol) and interoperable with any MRCPv1 or v2 clients. Thanks to their complete support for all major IETF and W3C standards, they enable speech technologies to be integrated into any platforms running applications based on voice interaction, such as VoiceXML (News - Alert) 2.0 or 2.1.

Recently, Loquendo announced the launch of Loquendo ASR 7.9 with enhanced recognition performance and a series of new features.

Loquendo ASR has added the Arabic language, while the acoustic models for US English have been improved, resulting in more accurate recognition of names and addresses for enhanced performance in contexts such as voice activated dialing, customer self-service and navigation.

With this new feature, performance has been further enhanced by a new algorithm for computing confidence scores for the whole utterance; improving recognition-error rejection. The Loquendo N-best algorithm has also been revised for a reduced response time and faster recognition.