IN-DEPTH

Many of our innovations in speech technologies were recently presented at the SpeechTEK WEST 2006 conference in San Francisco. To give our readers an idea of the many new and advanced features offered by Loquendo TTS, the main article of this issue will be Loquendo′s contribution to the AVIOS (Applied Voice Input/Output Society) Symposium at SpeechTEK WEST 2006, in a session dedicated to advances in TTS techniques. Thanks to AVIOS for allowing us to reproduce the submitted article, which will soon be published in the proceedings of the symposium.

>> Go to the article.

STANDARDS CORNER

• W3C releases Last Call Working Draft of Pronunciation Lexicon Specification
  January, 31 2006
  The Pronunciation Lexicon Specification (PLS) 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 for developers, while supporting the accurate specification of pronunciation information for international use.
  The PLS is a Last Call Working Draft that, means it is functionally complete and is available for public review. Send comments to www-voice@w3.org before March 15 2006.
  This is an important step towards the W3C Recommendation goal, and Loquendo is author of this W3C specification.
  
  
• Loquendo Submitted an Implementation Report for W3C SISR Specification
  February, 1 2006
  The W3C Semantic Interpretation for Speech Recognition (SISR) specification has reached Candidate Recommendation status. At this stage, companies are called upon to demonstrate the implementability of the specification, before moving on to the final stage of W3C Recommendation.
  Loquendo is the first company to announce the implementation of SISR in Loquendo ASR, together with Loquendo Speech Suite and VoxNauta™ platform. The adoption of SISR enables grammar developers to use a standard powerful script-language to validate and return semantic results from speech recognition.
  See the official results presented to W3C.
  
  
• W3C releases working draft of State Chart XML (SCXML)
  January 24, 2006
  The State Chart XML (SCXML), is a general-purpose event-based state machine language that can be used in many ways, including:
  • As a higher-level dialog language controlling VoiceXML 2.0 or VoiceXML 3.0′s encapsulated speech modules.
  • As a voice application metalanguage, where in addition to VoiceXML 3.0 functionality, it can also control database access and business logic modules.
  • As a multimodal control language in the MultiModal architecture, combining VoiceXML 3.0 dialogs with dialogs in other modalities including keyboard and mouse, ink, vision, haptics, etc.
  • As the state machine framework for a future version of CCXML.
  This new working draft is available for public review and comments are welcomed at www-voice@w3.org.
  
  

LOQUENDO Products

• Loquendo Awarded "Best Innovation in Speech Synthesis" at SpeechTEK West 2006
  February 20, 2006
  Loquendo announced that the Loquendo TTS text to speech engine has been awarded the "Best Innovation in Speech Synthesis" prize at AVIOS-SpeechTEK West 2006, in San Francisco. The prize was awarded for Loquendo′s ′Expressive Cues′ software, the first of its kind, which offers customers a comprehensive range of highly expressive phrases/exclamations for inserting into a text to render Loquendo's voices ever more emotive and lifelike.
  >> More
• Loquendo Extends its Reach in the Mobile World Introducing its Embedded TTS on WinCE 5.0 and Windows Mobile 5.0 devices
  February 13, 2006
  Loquendo has announced that Loquendo′s Text To Speech technology is now available for the latest compact versions of Windows: Windows CE 5.0 and Windows Mobile 5.0.
  The porting of Loquendo TTS to these new environments has provided a valuable opportunity to introduce, into the embedded version, the full range of improvements and enhancements already carried out on the Loquendo TTS core engine, originally derived from the multimedia/telephony sectors.
  >> More
• Loquendo′s VoxNauta™ Platform Awarded VoiceXML 2.0 Certification
  January 31, 2006
  Loquendo′s Voxnauta™ VoiceXML platform was awarded VoiceXML 2.0 platform certification by the VoiceXML Forum. The VoiceXML Forum′s Certification Program certifies that implementation platforms conform to the VoiceXML 2.0 test suite.
  This significant achievement demonstrates, once more, Loquendo′s ongoing commitment to providing high quality speech solutions based on open standards. Loquendo′s VoxNauta™ 7.0 VoiceXML platform also fully supports all other relevant speech standards, integrating Loquendo′s technologies through MRCPv2, IETF standard protocol; supporting W3C VoiceXML 2.1; and implementing CCXML 1.0, the new W3C standard language for programming call control at service level.
  >> More
• Loquendo Launches New Text-To-Speech Technology: Loquendo TTS 7 Series
  January 30, 2006
  Loquendo presented the latest version of its TTS voice engine, incorporating several dramatic leaps forward in terms of quality (fluency, naturalness, and accuracy) of pronunciation across the full range of the 39 Loquendo voices in 17 languages.
  Fluency has seen major advances thanks to the development of Concatenation Smoothing, successfully resolving acoustic discontinuities in the speech synthesis. Naturalness has been enhanced by the refinement of phrasing and prosody. Accuracy of pronunciation has been strengthened by the use of the Morphological Analyser, which examines word structure to resolve pronunciation ambiguities.
  Furthermore, you can now create your own customised voices, apply reverb and stereo effects to any read text, and use the Loquendo LexEditor tool, where you can insert your own phonetic transcriptions of specific names or words.
  >> More

Clients & Partners

• Loquendo and Code Factory Announce a Partnership Agreement to deliver solutions for the visually impaired
  February 14, 2006
  Loquendo and Code Factory, leading provider of software solutions for mobile professionals and the blind, announced that they are joining forces to deliver best-of-breed applications to the visually impaired. Through this agreement, Code Factory will integrate Loquendo′s embedded multilingual Synthetic Speech technology in its wide variety of mobile applications, enriching their user-experience.
  Code Factory has extensive experience in developing speech-enabled mobile software, from screen readers to hi-tech applications, aiding people with visual disabilities across the globe. Loquendo offers a high quality, multi-lingual portfolio of speech technologies, including the Loquendo Embedded TTS which currently supports 17 languages from around the world, with additional language technologies under development.
  >> More
• H-Care partners with Loquendo to boost its Human Digital Assistant
  January 30, 2006
  Loquendo and H-Care, the leader in developing user-friendly platforms for multi-channel self-service and customer care systems, announced a new initiative that provides a real breakthrough in CRM applications.
  Loquendo offers a complete line of innovative solutions for developing interactive speech applications that run on desktops, servers and embedded systems, guaranteeing the best solutions in speech synthesis, automatic speech recognition, voice recognition, and service creation tools.
  Loquendo′s advanced speech technology has been integrated within the H-Care′s innovative digital-assistant platform; in particular, Loquendo′s TTS engine will enable H-Care′s product, Human Digital Assistant, to interact with the client using the best quality speech synthesis available on the market.
  >> More
• Loquendo and Aculab Certify Interoperability of Loquendo Speech Suite 7.0 by MRCP
  January 23, 2006
  Aculab, a leading provider of enabling technology for the communications market, and Loquendo announced that Loquendo′s Speech Technologies software is compliant with the Aculab MRCP (Media Resource Control Protocol) client interface, for use with Aculab′s Prosody Media Processing Resources.
  Loquendo has been the first to implement the advanced MRCPv2 standard, which is supported by Aculab′s speech enabling interface. MRCPv2 utilises SIP, rather than RTSP, to control speech resources, as well as supporting additional functionality, including speaker verification and identification, record and grammar enrolment. Both Aculab and Loquendo interfaces also include the option of using MRCPv1.
  >> More

EVENTS

• Desayunos de Trabajo - Altitude,
  
  • 21 February 2006 – Portales de Voz
    Madrid, Augustin de Foxá, 25 – Pta. 12
  • 23 February 2006 – Portales de Voz
    Barcelona, Hotel Jazz - Pelai, 3
  • 4 April 2006 – Portales de Voz
    Bilbao
  
  
• TAL Conference 2006,
  Rome, Aula Magna del Ministero delle Comunicazioni, 9-10 March 2006.
  
  
• CeBIT 2006,
  Hannover, Germany, 9-15 March 2006.
  
  
• ACE 2006,
  Budapest, 4-7 April 2006
  San Francisco, 8-11 May 2006.
  
  
• SpeechTEK 2006,
  New York, Marriott Marquis, 7-10 August 2006.