IN-DEPTH

In this issue, the Loquendo team who participated in SpeechTEK 2007 would like to share the feedback it received from those attending this important event, along with the experiences and insights gained from the conference on the state of the speech market and current and future trends.
We hope you will find it interesting.

>> Go to the article.

Loquendo News

• Loquendo Awarded "Market Leader - Best Speech Engine" at SpeechTEK 2007
  September 5, 2007
  Loquendo announced that on Aug. 22 the company was awarded "Market Leader - Best Speech Engine" at the 2007 SpeechTEK Conference and Exposition in New York.
  The award recognizes companies that have led the industry over the past 12 months in specific categories. The winners were selected by the editors of Speech Technology magazine alongside an independent panel of industry analysts and experts.
  According to Speech Technology magazine analysts, the prize was awarded for Loquendo's "experience with international markets and the multitude of languages that make up those markets, which is reflected in its speech engines.
  >> More

STANDARDS CORNER

• Third working draft of SSML 1.1 is published
  September 4, 2007
  The W3C Voice Browser working group (VBWG) published the third Working Draft of Speech Synthesis Markup Language (SSML) Version 1.1. This document enhances SSML 1.0 specification to provide better support for a broader set of natural (human) languages. It aims to determine in what ways, if any, SSML is limited by its design with respect to supporting languages, that are in large emerging markets, for speech synthesis technologies, but for which there was limited or no participation by either native speakers or experts during the development of SSML 1.0. Recent changes include: specific markup for tokens, clarified language on xml:lang attribute, and new attributes on speak and audio elements.
  For details on this draft of the SSML 1.1 specification, click here.
  
  
• Workshop on W3C's Multimodal Architecture and Interfaces
  August 28, 2007
  The W3C Multimodal Interaction working group (MMIWG) seeks to extend the Web to allow users to dynamically select the most appropriate modes of interaction for their current needs. The Multimodal Architecture and Interfaces (MMI Architecture) specification is designed to provide a general and flexible framework providing interoperability among modality-specific components from different vendors - for example, speech recognition from one vendor and handwriting recognition from another. In order to make the MMI Architecture more useful in current and emerging markets, the MMIWG is interested in suggestions on how to improve the use of the architecture to support and integrate various user interfaces on multimodal devices e.g. speech, GUI and Ink.
  The worshop will be hosted by W3C/Keio, in Fujisawa, Japan (16-17 November 2007). To participate a position paper need to be sent by email to member-mmiws-submit@w3.org before 15 October 2007.
  To read more information about the Workshop on W3C's Multimodal Architecture and Interfaces, click here.
  
  
• AVIOS Student Application Contest 2007
  September 12, 2007
  The Applied Voice Input/Output Society (AVIOS) announced their second student application contest to demonstrate creativity and programming skills in voice or multimodal applications to be developed and submitted to AVIOS by January 31st 2008.
  This year students may use any of a variety of platforms, including Loquendo Café.
  For the AVIOS Student Speech Application Contest Entry Form, click here.
  
  
• New Draft of IETF MRCP version 2
  September 4, 2007
  IETF SpeechSC working group recently released an update of the Media Resource Control Protocol version 2 (MRCPv2), which is draft number 13 in Last Call Working Draft stage.
  The recent updates include clarifications, fixes to the ABNF protocol definition, other minor editorial changes, and very few content changes. To help the progress of MRCPv2 to a final stage of specification, declarations of implementation are welcome.
  Please send any reports or comments to speechsc@ietf.org.
  
  

R&D COLLABORATIONS

• Loquendo R&D in HOPS IST project
  In May 2007, the three year FP6 HOPS project was successfully concluded, addressing the large-scale deployment of new online public services supported and accessible by voice channels. The project made significant contributions to the availability of a multi-channel, multi-modal and multi-device advanced hub, able to be integrated with existing supporting systems and applications, thus enabling the launch of advanced and fully interactive Online Public Services. The project aim was to enhance the particular functionalities of the three technologies involved (Voice, Natural Language and Semantic Web), defining a kind of advanced front-end (hub).
  HOPS most important contribution has been to drive a re-engineering of business processes at existing call centres by introducing a way to provide automated voice services more sustainably. In order to validate its results, HOPS produced fully functional prototypes tested and validated by the three Local Authorities involved in the project: Barcelona, London Borough of Camden, and Torino.
  The HOPS consortium was composed of 13 partners: Municipality of Barcelona (Spain), Municipality of Turin (Italy), London Borough of Camden (UK), Sun Microsystems (Spain), Loquendo (Italy), iSOCO (Spain), CSI (Italy), CSP (Italy), IT-Deusto (Spain), Runtime Collective (UK), Universitat Politècnica de Catalunya (Spain), University of Turin (Italy), Universiteit van Amsterdam (The Netherlands).
  >> More
  
  
• HOPS will go on! - Interviews with representatives from Camden, Torino and Barcelona
  The HOPS project focused on the deployment of advanced ICT "voice-front-end public platforms" enabling European citizens to access their public authorities, and to make more efficient current e-government services, that presently suffer from significant performance shortcomings. Additionally, interaction by voice improves web accessibility and usability, especially for the differently able.
  Three interviews with representatives from Camden, Torino and Barcelona City Councils, give their perspectives on vocal services within a public administration.
  >> More
  
  
• HOPS humanises e-government call systems - ICT Results e-bulletin
  Public administrations face growing pressure to provide better services and, at the same time, to trim costs. Traditional automated call centres were heralded as the solution, but many people have expressed a dislike for using them. Thanks to the EU HOPS project, callers to public authorities will finally be talking to 'intelligent' machines using a mixture of natural and scripted dialogue.
  The IST EU programme, now ICT, in its first Newsletter issue (ICT Results e-bulletin) reports HOPS's most significant outcomes.
  >> More
  
  
• Report from Interspeech 2007 conference
  In this interview, we report some of the impressions and evaluations of three Loquendo researchers from Interspeech 2007, one of the most important academic conferences of the year.
  The contributions given at Interspeech include: research reports on two EC-funded projects (SHARE and HIWIRE) and the results obtained from a system developed by Loquendo and the Politecnico of Torino, which was used in NIST competition: "Speaker Recognition Evaluation 2006" (SRE06).
  >> More
  
  

LOQUENDO Products

• New Release of Loquendo TTS
  August 20, 2007
  Loquendo announced the release of Loquendo TTS 7.3. This new version of the text-to-speech technology provides many key new features and supports the Turkish language with the brand new voice of Kerem.
  The latest Loquendo TTS release has been enriched with a powerful Java API layer which makes all TTS features available to Java programmers as well.
  With the new Dynamic Range Control algorithm, integrated in the TTS engine, users can now benefit from improved voice intelligibility in any noisy environment. Simply using runtime controls, prompts can easily be fine-tuned and audio easily adapted to specific speakers and audio devices. >> More
  
  
• Loquendo Launches Turkish. Introducing Kerem, the Brand New Male Turkish Voice.
  August 8, 2007
  Loquendo is proud to present Kerem, the brand new male Turkish voice. With the voice of Kerem, Loquendo extends its reach into the Eastern European market and worldwide, enabling the company to support its partners ever more effectively in the expanding Turkish market, and around the world for Turkish speaking users. Kerem brings the total number of languages in the Loquendo portfolio to 21, with the total number of voices now at 51.
  Like all of Loquendo's voices, Kerem is available for Telephony, Multimedia and Embedded applications, allowing integrators to select the footprint that best suits their requirements, and guaranteeing the same wide range of high-quality voices and languages all with the same core engine.
  To meet Kerem, click here.
  To meet the Loquendo TTS family, click here.
  >> More
  
  

Clients & Partners

• VoxIQ Selects Loquendo Technologies to Enable Complex Conversational Speech Recognition and Text To Speech
  September 26, 2007
  Loquendo and VoxIQ, the innovative UK company that is set to revolutionise the speech market, have combined the VoxIQ technology with Loquendo's award-winning speech technologies.
  The VoxIQ product uses Loquendo ASR through Loquendo VoxNauta to eavesdrop on a conversation between people while providing support, such as filling in forms automatically or displaying data in line with the changing conversation. It also uses Loquendo ASR together with Loquendo TTS synthetic speech to allow conversation with a person in a new and intelligent way, known as 'conversational self-service'.
  >> More
  
  
• Loquendo Successfully Completes Interoperability Testing Between Genesys Voice Platform and Loquendo Speech Engines
  September 20, 2007
  Loquendo announced that the interoperability testing of the Genesys Voice Platform and Loquendo's state-of-the-art, multilingual speech engines has been successfully completed. Testing of both IP and TDM based integrations of the GVP 7.2 MR1 and Loquendo Speech Suite version 7.0, including Loquendo TTS and Loquendo ASR has had a positive outcome and Genesys Product Management has approved the support of Loquendo implementations on the GVP. Now Genesys customers can also draw all the benefits of Loquendo's award-winning speech technology.
  The interoperability between the GVP 7.2 MR1 and Loquendo TTS and ASR connected through a client-server architecture, is based on the quick and easy-to-use remote access features provided by the Loquendo Speech Suite and by the MRCP standard protocol.
  To upgrade now your Genesys platform to Loquendo ASR & TTS, click here.
  >> More
  
  
• SchoolMessenger Chooses Loquendo's Text-to-Speech for School Notification Applications
  August 21, 2007
  Loquendo and SchoolMessenger, a leading provider of notification solutions for education, announced the selection of Loquendo speech technology for SchoolMessenger's innovative line of notification products.
  With more than 6,000 school districts, public schools, colleges, universities, private schools and other educational facilities using its notification products, SchoolMessenger is recognized as a trusted partner for helping educators communicate with parents, staff and students. Whether sending a routine notification about student absence, or broadcasting a rapid alert in response to an emergency, school leaders need to know that their message is heard.
  Loquendo TTS is used to personalize messages across the line of SchoolMessenger notification products, including applications for K-12 in which a parent can keep informed about important topics related to the academic performance, attendance and safety of students. Data-driven voice messages, using Loquendo TTS, are an important component of SchoolMessenger's blended messaging approach, which includes recorded voice, text-to-speech, SMS text messaging and email, to reach a wide audience in a short period of time with personalized communications.
  >> More
  
  

EVENTS

• Call Centre Expo 2007,
  Birmingham NEC, UK, September 26-27, 2007.
  Visit Loquendo at Stand G40.
  
  
• SMAU 2007,
  44th ICT International Expo
  Fiera Milano (Nuovo Quartiere Rho-Pero), Milan, Itay, October 17-20, 2007.
  Visit Loquendo at Telecom Italia ICT Campus, Padiglione 24 Stand A02-C01 A14-C11.
  
  
• VoiceDays 2007,
  Bonn, Alter Bundestag, Germany, October 17-18, 2007.
  Visit Loquendo at Stand C02.
  
  
  • Wednesday, October 17, 2007
    Demo Forum - Platform & Tools
    Loquendo Speech Development Tools
    15:35 pm - 16:20 pm (INLOQ/Loquendo)
    
    
  • Thursday, October 18, 2007
    Demo Forum - Platform & Tools
    Analysing and Tuning Voice Systems with Loquendo Technologies
    13:15 pm- 14:00 pm (INLOQ/Loquendo)
  
  
• Expo Call Center & CRM Solutions 2007,
  IFEMA, Feira de Madrid, Palacio Norte, Madrid, Spain, November 7-8, 2007.
  
  
• Expo Call Center & CRM Solutions 2007,
  Estoril Congress Center, Estoril, Portugal, 27-29 November 2007.
  
  
• Navigation USA 2007,
  San Francisco Bay, USA, November 29-30, 2007.
  
  
• ISS WORLD 2007,
  Washington DC, USA, December 10-12, 2007.