Global speech technology provider, Loquendo, has announced its congratulations for Multimodal Interaction Working Group for the publication of the Extensible MultiModal Annotation Markup Language (EMMA) as a W3C (News - Alert) Recommendation.

Designed to be a powerful language, EMMA benefits MultiModal applications, such as voice applications, by boosting performance through the provision of an enhanced interpretation of inputs through voice and other modalities. As the use of speech and voice technologies increase, EMMA has significant applications throughout the Web.

EMMA contributes to the value of speech-enabled applications as it helps to create a richer presentation of speech input in the form of annotated ASR results, which can then be integrated into a voice platform. By improving the quality of speech, more companies will be able to implement self-service portals to support a growing customer base.

An XML markup language, EMMA represents the interpretation of user input and annotations for confidence scores, timestamps, input medium and more in speech-enabled and multimodal applications.

The Web is expected to become more accessible to more people and from more devices as a result of the EMMA 1.0 standard. The implementation of this standard will enable multimodal interaction through handwriting, natural language, gestures and speech. All of this will be in addition to the usual keyboard and mouse use.

These advancements help to encourage the development of rich Web applications at lower cost as it will provide especially valuable for mobile phone application developers by facilitating and simplifying the creation of applications making use of inputs such as speech, touch screens, stylus and more.