IN-DEPTH

In this issue the main topic is devoted to describing a new standard that is emerging from the W3C Voice Browser WG. It is called W3C Semantic Interpretation for Speech Recognition and has already been implemented in the latest release of Loquendo ASR. This standard allows a speech recognition engine to produce formatted results, to perform consistency checks and other processing on recognition results. The article provides a description of the standard and gives a set of progressive examples that are intended to clarify the formalism and its relevance in speech applications.

>> Go to the article.

STANDARDS CORNER

• W3C Celebrates Its Tenth Anniversary
  December 1, 2004
  The World Wide Web Consortium celebrated its tenth anniversary, ten years of its mission to lead the Web to its full potential. On December 1st, W3C Members, Team, invited speakers, and international media gathered in Boston, USA to reflect on the progress of the Web, the risks and chances facing the Web during W3C's second decade. "This special anniversary brings the opportunity to acknowledge the impact of the Web and the W3C's stewardship role," said Tim Berners-Lee, W3C Director. "I hope it will also inspire ever more collaboration, creativity, and understanding across the globe."
  In a proclamation issued December 1st, Massachusetts Governor Mitt Romney declared December 2004 to be World Wide Web Consortium Month.
• CCXML 1.0 Last Call Published
  January 11, 2005
  Addressing comments received during the previous Last Call WD, the Voice Browser Working Group has published an updated Last Call Working Draft of CCXML Version 1.0. This standard, the Call Control eXtensible Markup Language, provides telephony call control support for VoiceXML and other dialog systems. The next step is to develop an Implementation Report to be used to test the implementability of this language.
• Semantic Interpretation for Speech Recognition is a Last Call Working Draft
  November 8, 2004
  This document defines the process of Semantic Interpretation for Speech Recognition as well as the syntax and semantics of semantic interpretation tags. These tags can be added to speech recognition grammars to compute information to be returned to an application. This occurs on the basis of rules and tokens that were matched by the speech recognizer. In particular, it defines the syntax and semantics of the contents of Tags in the Speech Recognition Grammar Specification (SRGS 1.0).
• CSS3 Speech Module Published
  December 16, 2004
  The CSS Working Group has released an updated Working Draft of the CSS3 Speech Module. The Cascading Style Sheets (CSS) language is used to render structured documents like HTML and XML on screen, on paper and in speech. The draft defines aural properties that match the Speech Synthesis Markup Language (SSML 1.0) model.
• New Working Draft released for EMMA
  December 14, 2004
  The Multimodal Interaction Working Group has released an updated Working Draft of EMMA. The Extensible MultiModal Annotation language (EMMA) is a data exchange format for interaction management systems. As part of the W3C Multimodal Interaction Framework, this specification defines markup for describing user input together with annotations, such as, confidence scores, timestamps and input medium. This version includes the associated XML schema!

USE CASES

This new section describes an integration success story of Loquendo's technologies and platforms, in real-life applications. This first issue will concentrate on the field of banking systems automation. We'll be talking to Maurizio Copperi, Senior Project Manager at Citec Voice - the person who managed the development and integration of the application, which is called Voice Trading On-line, for one of the largest Italian banking groups: Banca Intesa.
Citec Voice is part of the Citec Group and is the leading company for the design and implementation of speech applications in Italy.

>> Go to the article.

LOQUENDO Products

• Loquendo ASR Now Supports W3C's Semantic Interpretation for Speech Recognition, ETSI Aurora Distributed Speech Recognition and the Dutch language
  January 19, 2005
  This new version of the Loquendo ASR speech recognition software (Loquendo ASR 6.5) includes important application development enhancements and supports the following new features:
  • a new formalism for grammar semantic interpretation tags, in accordance with the latest working draft of W3C Semantic Interpretation for Speech Recognition. The main article of this newspaper gives a detailed description of this new language;
  • Distributed Speech Recognition (DSR) according to ETSI ES 202 050 and ES 202 212 specifications which allows the improvement of robustness to background noise and to aviod degradations caused both by the codec and by the effects of transmission errors;
  • the Dutch language alongside other 15 languages.
  >> More
• Meet Saskia, the new Loquendo Dutch Female Voice!
  December 23, 2004
  Loquendo is pleased to announce Saskia, the new bubbly Dutch female voice to accompany Willem, the Dutch male persona. Loquendo's multilingual portfolio of lifelike synthetic speech is rich as never before.
  To listen to the synthetic voices of Saskia and Willem and their expressivities, please click here.
  To meet the Loquendo TTS family, please click here, where you can also try the Loquendo TTS online interactive demo. >> More
• Loquendo Unveils Loquendo TTS Director to Design Effective Prompts for Speech Applications
  December 16, 2004
  Loquendo TTS Director is a multi-platform Java development tool, which supports users in designing effective prompts for their applications. Text is written and interactively refined through a "listen & edit" procedure, which allows fine-tuning for even better TTS performance. >> More

Clients & Partners

• Share Project: Loquendo TTS at the service of Dortmund Firefighters
  December 20, 2004
  The project SHARE develops a ‘Push-To-Share’ advanced mobile service, providing critical multimodal communication support for emergency teams during rescue operations. Based on advanced, innovative technologies, and shared structured multimodal information resources, it allows mobile workers to naturally and bi-directionally communicate. The targeted language will be German, for which a special tuning of Loquendo TTS will be performed in order to grant perfect pronunciation, e.g. of street names to be reached, along with the experimentation of prosodic and acoustic processing to ensure perfect intelligibility and effectiveness in the typical noisy conditions of rescue operations. >> More
• Loquendo and Eicon Networks sign a Partner Agreement
  November 24, 2004
  Loquendo, the global speech technology company, and Eicon Networks Corporation, a global provider of communication products for networked business applications, announced today that have signed a partnership agreement.
  Eicon Networks, a leading manufacturer of networking products, together with its Eicon Technology Partner Program, can offer robust, flexible and highly reliable solutions. Loquendo offers a broad range of innovative solutions to create voice services, Call Centers automation, voice automation features in the CRM applications, Intranet and Unified Messaging and the creation of info mobility solutions. >> More

Events

• AVIOS/TVUI/SpeechTEK West 2005,
  San Francisco, Hotel S.F. Marriott, 21-23 February 2005
  
  
  • "Phonetic Learning tool to face user formulations variability and pronunciation variants" (Rosanna Duce)
  • "Latest advancements in TTS: Mixed-language Support and Audio Mixer" (Piergiorgio Vittori)
  • "Helping Visually Impaired People with Embedded Speech Technologies" (Silvio Nasi)
  
  
• ININ EMEA Partner Conference,
  Sheraton Airport Hotel, Schiphol, Amsterdam, The Netherlands, 1-2 March 2005
• GENESYS Partner Forum,
  Rome, 3-4 March 2005
• Voice World Europe 2005,
  London, Olympia Conference Center, 4-5 May 2005