STANDARDS CORNER

• Internationalizing the Speech Synthesis Markup Language Workshop III in India
  January 13-14, 2007
  The W3C Voice Browser Working Group is organizing a third Workshop on "Internationalizing the Speech Synthesis Markup Language" in Hyderabad (India), in order to solicit additional suggestions to increase the use of SSML for other non-English languages. The group is especially interested in suggestions on how to improve the rendering of languages, such as Arabic, Hebrew, and the Indian languages Telugu, Hindi, Bengali, Punjabi, Gujarthi, Urdu. The worshop will be hosted by Bhrigus Sotfware and the International Institute of Information Technology (IIIT) in Hyderabad, India.
  
  
• Multimodal Architecture and Interfaces Working Draft Published
  December 11, 2006
  The W3C Multimodal Interaction Working Group released a new working draft on "Multimodal Architecture and Interfaces".
  This document describes a loosely coupled architecture for multimodal user interfaces, which allows for co-resident and distributed implementations, and focuses on the role of markup and scripting, and the use of well defined interfaces between its constituents.
  Comments for this specification are welcomed, please send them to www-multimodal@w3.org, the public email list for issues related to Multimodal.
  
  
• New Working Draft of CCXML specification
  November 22, 2006
  A new Working Draft of "Voice Browser Call Control: CCXML Version 1.0" has been published by W3C Voice Browser Working Group.
  The MRCPv2 protocol allows client hosts to control media service resources such as speech synthesizers, recognizers, verifiers and identifiers residing in servers on the network.
  This Working Draft addressed many of the comments that came up during the Last Call review period and a number of minor changes that came up during the implementation report development. A new Last Call Working Draft publication is expected soon.
  
  
• Semantic Interpretation for Speech Recognition Released as Last Call Working Draft
  November 3, 2006
  Following the publication of this specification as Candidate Recommendation (Jan. 2006), a substantive change was required to remove the starttime/endtime feature. A non-normative version of this specification highlighting the changes since the previous version is available, click here.
  This specification defines the syntax and semantics of semantic interpretation tags that can be added to speech recognition grammars (SRGS) to compute information to return to an application on the basis of rules and tokens that were matched by the speech recognizer.
  
  
• Pronunciation Lexicon Specification Re-published Last Call Working Draft
  October 26, 2006
  The W3C Voice Browser Working Group re-published as a Last Call Working Draft the "Pronunciation Lexicon Specification (PLS) Version 1.0".
  The PLS markup is designed to enable interoperable specification of pronunciation information for both ASR and TTS engines within voice browsing applications. The language is intended to be easy to use by developers while supporting the accurate specification of pronunciation information for international use.
  
  
• Chair's Reports on the Voice Browser and Multimodal meetings in Oslo
  September 18-22, 2006
  Click here for the chair's report on the Multimodal Interaction meeting which was held on September 18-19, or click here for the chair's report on the Voice Browser meeting held on September 21-22.
  A joint meeting of the two W3C Working Groups was held on September 20 with the participation of Lager Torbjoern from the Linguistics department of Goeteborg University. The meetings were hosted by Opera Software in Oslo.
  
  

R&D COLLABORATIONS

• Loquendo ASR in the HIWIRE Project
  Loquendo provides its ASR technology for the EU-funded HIWIRE (Human Input that Works In Real Environments) project, which aims to make considerable improvements to the robustness, naturalness and flexibility of vocal interaction between humans and machines, focusing on aeronautics.
  Speech recognition systems often fail to meet the demands of applications under adverse conditions. HIWIRE project has achieved significant improvements in ASR performance in noisy environments and for non-native speakers.
  HIWIRE project showed the results achieved in the first two years during the IST exhibition on 21-23 November 2006 in Helsinki.
  >> More
  
  
• Kick-off Meeting of COMPANIONS Project in Oxford
  November, 9-10 2006
  COMPANIONS (Intelligent, Persistent, Personalised Multimodal Interfaces to the Internet) project aims at making ECAs (Embodied Conversational Agents) a reality by developing the next generation of technologies for them. It is a newly co-funded EU 6th Framework project.
  It relies on a rich background of human languages technologies developed by its partners, such as dialogue technologies and high quality text-to-speech. An emphasis within COMPANIONS is the heavy reliance on machine learning techniques to relieve the traditional bottleneck of language technologies.
  The kick-off meeting took place in Oxford, St. Hugh's College on the 9th and 10th November.
  The consortium is composed of partners from United Kingdom, Czech Republic, Sweden, USA, Finland, France, Spain and Italy.
  Find out more at http://nlp.shef.ac.uk/companions/.
  
  
• C@R: Collaborative Platform for Working and Living in Rural Areas
  September, 11-12 2006
  C@R (Collaboration@Rural), is an Integrated Project, co-funded by the IST programme of the European Commission's 6th Framework which aims to boost the introduction of Collaborative Working Environments (CWE) as key enablers catalyzing rural development.
  From the technical standpoint, C@R will organise the work in three layers:
  • Rural Living Labs
  • Software Collaborative Tools
  • Collaborative Core Services
  The kick-off meeting took place in Madrid at Tragsa premises on the 11th and 12th of September.
  The consortium includes partners from Spain, Greece, Finland, Germany, Austria, France, Belgium, United Kingdom, Israel, Hungary, Czech Republic, Poland, China, Brazil, Italy.
  Find out more at http://c-rural.eu/.
  
  Find out more about Loquendo R&D Cooperations, click here.
  
  

LOQUENDO Products

• New Language for Loquendo ASR: Polish
  December 12, 2006
  Loquendo announced the availability of Loquendo ASR in Polish. Having released the Polish TTS voices of Zosia and Krzysztof earlier in the year, Loquendo's robust and high performing speech recognition technology has now been ported to Polish.
  With the Polish language, Loquendo is making inroads into the rapidly expanding markets of Central Europe and beyond. Loquendo can thus give complete support to its partners in a European Union undergoing continual growth and diversification.
  This is the first time Loquendo has ported its speech technology to a Slavonic language, so opening up for future development a new and important linguistic family. In doing so, Loquendo has demonstrated it can easily transfer its state of the art technology to any language of any linguistic branch, thereby creating opportunities in markets throughout the world.
  >> More
  
  
• Loquendo Announces New Release of Loquendo ASR with Partial Results Recognition and Grammar Caching
  December 4, 2006
  New interesting features have been recently released in the Loquendo ASR product. During the speech recognition process Loquendo ASR gives partial results as soon as they are available, rather than once the caller has finished speaking. This is particularly useful for long utterances: for instance, a caller giving their credit card number over the phone doesn't waste time completing an invalid number because incorrect formulations are identified straightaway.
  The process of recognition has been further accelerated by Grammar Caching: grammars, once compiled, can be stored in cache ready for subsequent use, rather than being discarded and then laboriously recompiled each time. Consequently, if a caller utterance is repeated during a call it will have the corresponding grammar already compiled.
  >> More
  
  
• Loquendo Presents the Brand New Castilian Spanish Voice
  October 30, 2006
  Loquendo, leading innovator in speech technology, is proud to present Leonor, the brand new Castilian Spanish female voice.
  Leonor complements Loquendo's existing Castilian-speaking voices, Jorge, Carmen and Juan, enabling the company to support its partners ever more effectively in the vitally important and rapidly expanding Spanish market.
  Loquendo is the very first speech technology company to offer an emotional component, achieving truly lifelike speech with a far wider emotional range, representing a major leap forward in speech technology.
  To hear Leonor for yourself click here, and to hear the whole Loquendo Spanish-speaking family, click here.
  >> More
  
  

Clients & Partners

• Brazil's Quatro Rodas Travel Guide Launches Interactive Web Portal Incorporating Loquendo Speech Technology and Bizvox Speech Solutions
  November 20, 2006
  Loquendo and Bizvox, provider of speech recognition solutions for the telecommunications market, announced the integration of Loquendo's award-winning speech technologies into the website voice portal for the Quatro Rodas Travel Guide.
  The Quatro Rodas Guide includes vast amounts of information on every aspect of travel, and much of this information is now available via the Disk G4R voice portal. Bizvox's innovative solution allows customers to access information on the 16,000 businesses that are included in the travel guide, by means of a single phone number charged at local rates from anywhere in Brazil.
  The new service uses the Loquendo VoiceXML Platform incorporating Loquendo ASR and Loquendo TTS, and so the Quatro Rodas Travel Guide is now more accessible than ever. Loquendo's new, leading edge, multimedia technologies make G4R ever more user friendly and ever more popular - an indispensable tool in the life of the Brazilian traveller.
  >> More
  
  
• Altitude Voice Portal and Loquendo Technology Deliver Superior Self Service for Coopervision
  November 6, 2006
  Altitude Software, a leading independent contact centre solutions vendor, and Loquendo announced the implementation of a Self Service solution at the Coopervision Spain Contact Center.
  Coopervision Spain is a subsidiary of the global leader in contact lens manufacturing, focused on maintaining high levels of customer satisfaction with retail customers worldwide. CooperVision Spain is a pioneer, among the company's global subsidiaries, in the adoption of systems for making spoken communication possible between people and computers.
  >> More
  
  

EVENTS

• SpeechTEK WEST 2007,
  Hilton San Francisco, BOOTH #314 Grand Ballroom, Hilton & Towers - San Francisco, California, 21-23 February 2007.
  
  
• ACE 2007,
  The Marriott Marble Arch, London - UK March 12-14, 2007.
  
  
• Vocalexpo 2007,
  CNIT - Paris, La Défense - March 13, 2007.
  
  
• ACE 2007,
  Scottsdale, Arizona - USA, The Renaissance Scottsdale Resort - March 26-28, 2007.
  
  
• SpeechTEK 2007,
  New York, Marriott Marquis, BOOTH #509, August 20-22, 2007.