Loquendo at SpeechTEK 2005

IN-DEPTH

Together with Loquendo ASR 6.7, Loquendo has released a new, powerful tool called Loquendo Acoustic Model Adaptation (Loquendo AMA), a means of greatly improving engine performance by adapting Acoustic Models, effortlessly and without the need for specific technical know-how. Loquendo AMA is an important new component of the Loquendo ASR tool-suite and can be used in conjunction with the Phonetic Learning tool (already described in Nov. 2004 described in Nov. 2004 on this newsletter) to improve the performance of speech applications.

Systems integrators can now easily make the recognition engine adapt to difficult conditions, such as ways of speaking (i.e. regional accents, fast speaking), different audio channels (i.e. wireless, multimedia microphone, PDA, etc), different environments (i.e. in-car, outdoors, public areas, factory), application-dependent vocabulary (e.g. specific jargon, such as aeronautic terms).

>> Go to the article.

STANDARDS CORNER

• VoiceXML 2.1 Specification Published as Candidate Recommendation
  June, 13 2005
  W3C's Voice Browser Working Group has released a new version of the Voice Extensible Markup Language (VoiceXML) 2.1 specification at Candidate Recommendation level. This a new important step towards the W3C Recommendation goal!
  VoiceXML Version 2.1 defines eight new features, either newly introduced or enhanced from VoiceXML 2.0. The purpose of VoiceXML 2.1 is to ensure their portability between platforms and at the same time maintain complete backwards-compatibility with VoiceXML 2.0.
  The next step will be to demonstrate the implementability of these very important features for developing VoiceXML applications today.
  
  
• CCXML Re-Published as Last Call Working Draft
  June 29, 2005
  The Voice Browser Call Control (CCXML) specification has been recently published for the third time as a Last Call Working Draft. This is fact is unsual, but demonstrates the great deal of interest that this new language has generated. The next step in the standardization process is to relase a test-suite for testing the implementabilty of the CCXML.
  
  
• State Chart XML (SCXML) Working Draft is Released
  July 5, 2005
  The W3C Voice Browser Working Group has released the first contribution for a new generation of Voice Browser application. This first working draft, which goes by the full name of: "State Chart XML (SCXML): State Machine Notation for Control Abstraction 1.0", describes a generic state-machine based execution environment based on CCXML and Harel State Tables. SCXML is a candidate for the control language within VoiceXML 3.0, CCXML 2.0, and the authoring language under development by the Multimodal Interaction Working Group.
  
  
• SSML 1.0 say-as is Published as W3C Note
  May 26, 2005
  A W3C Note has been released to define a set of standard values for the "say-as" element of the SSML 1.0 markup, which is the standard language developed by W3C Voice Browser for directing the behavior of a speech synthesizer in its processing of text to be spoken. The "say-as" element is used for semantic tagging of content to assist the processor in disambiguating ambiguous input. However, SSML 1.0 does not define the values of the attributes of the "say-as" element. This Note provides definitions for these attributes that cover many of the most common use cases for the "say-as" element.
  
  

LOQUENDO Products

• Loquendo Presents VoxNauta 7.0
  July 27, 2005
  Loquendo announces the availability of its new, optimized Voice Platform solution, VoxNauta 7.0, a simple yet scalable and powerful voice platform that allows the optimal exploitation of Loquendo TTS, Loquendo ASR, and Loquendo Speaker Verification technologies.
  VoxNauta 7.0, Loquendo’s multi-OS, software-only voice platform exploits all the most advanced W3C and IETF standards in the speech scenario in order to facilitate the task of advanced vocal application deployment. This includes the new VoiceXML 2.1 standard, as well as CCXML 1.0, the new standard language for programming call control at service level.
  Moreover Loquendo TTS, ASR and Speaker Verication technologies are integrated in Loquendo’s voice platform by exploiting MRCP v2. The new version of the VoxNauta platform allows service deployment with total compliance to SGRS (either XML and ABNF), SISR 1.0 and SSML 1.0.
  >> More
• Loquendo VoxNauta platform Linux based is now available
  July 8, 2005
  Loquendo announces an exciting new development in the VoxNauta™ platform, which will provide systems integrators worldwide with even greater development freedom: from today, the Linux version of Loquendo’s VoxNauta platform will be available based on Linux Red Hat 7.3. The extended support to Linux Operating System complements Loquendo’s existing support of the Microsoft Windows™ Operating System.
  The Linux release of the VoxNauta platform is based on the VoiceXML standard and the software-only implementation of the SIP-RTP protocol. It provides a thin, yet scalable, comprehensive software voice platform which incorporates the latest generation of Loquendo’s high-quality, top-performing speech technologies Loquendo TTS and Loquendo ASR.
  >> More
• New Loquendo ASR 6.7 Features Boost Recognition Performance
  July 6, 2005
  The new version of Loquendo’s Automatic Speech Recognition (Loquendo ASR 6.7) gives customers the means of greatly improving engine performance by giving them the necessary tools to efficiently adapt their own Acoustic Models, effortlessly and without the need for specific technical know-how.
  Systems integrators can now easily make the recognition engine adapt to difficult conditions such as way of speaking (i.e. regional accents, fast speaking), different audio channels (i.e. wireless, multimedia microphone, PDA, etc), different environments (i.e. in-car, outdoors, public areas, factory), application dependent vocabulary (e.g. some specific jargon, like aeronautic terms). Acoustic model adaptation dramatically improves recognition performance, using audio material recorded online by Loquendo ASR while the application runs.
  Furthermore, Loquendo ASR 6.7 also provides a powerful tool to achieve a more effective and user-friendly use of speech recognition in voice application development. With Voice Enrolled Grammars, end-users can vocally customize personal services, including personal agenda and contact management in Voice Activated Dialling services.
  >> More
• Loquendo presents New Expressive Voices
  June 15, 2005
  Loquendo presents two new Emotional TTS Voices: Italian personas Paola and Luca join Loquendo’s rapidly expanding portfolio of emotional voices.
  Loquendo is the first speech technology vendor to enable its customers to make their vocal messages expressive. Just like human conversation, expressive intention is conveyed through conventional formulas and interjections, which are pronounced naturally and colorfully. As a result, synthetic voice messages are truly lifelike and customers enjoy interacting with them even more.
  If you want to try our TTS Interactive Demo, click here!
  >> More

Clients & Partners

• Loquendo and New Bridges Announce a Strategic Partnership to Deliver Speech-Enabled Solutions
  June 29, 2005
  Loquendo today announced that it has entered into a partnership with New Bridges, Voice Processing Engineers. This agreement establishes the latter as a Value Added Reseller of Loquendo TTS and Loquendo ASR multilingual speech technologies for the European multimedia and telephony speech markets.
  Through this agreement, New Bridges will be offering its next-generation IVR solutions to call center providers throughout Europe. Loquendo's high-quality, multilingual speech technologies will open-up new markets for the leading Dutch IVR player, which will offer its solutions to call-center service providers mainly in the banking sector, as well as a range of solutions for the disabled and info-kiosks.
  >> More
• VoiceObjects integrates Loquendo technology
  June 23, 2005
  Loquendo and VoiceObjects, worldwide leader in Voice Application Management Systems (VAMS), today announced the interoperability between Loquendo’s multilingual VoiceXML platform VoxNauta™ and VoiceObjects X5™.
  VoiceObjects helps to expand telephony as a mass media just as it already supports innovative business models today, including Voice Commerce and the providing of Voice Applications Service. With VoiceObjects X5, customers can create, test, deploy and analyze voice application services through a single, tightly-integrated environment providing unique voice application server technology with full, multi-service, multi-tenant capabilities and cluster management.
  >> More
• Loquendo Strengthens Its Presence In France
  June 14, 2005
  Loquendo announces the opening of its new Paris office in response to the increasing demand for Loquendo’s market-leading speech technologies in France. Also to this effect, Mr. Philippe Poux has joined the company’s international team to distribute Loquendo technology throughout the country. Mr. Poux has extensive expertise in the speech technologies market.
  Loquendo technology has been in strong demand from French systems integrators for several years now and Loquendo has successfully asserted its presence on the French speech market. Loquendo is the first speech technology player to offer the French-speaking market truly communicative synthetic speech with the Expressive French voice of Loquendo TTS, Juliette. Click here to listen to Juliette.
  >> More
• Genesys integrates Loquendo technology
  June 13, 2005
  Loquendo and Genesys Telecommunications Laboratories, Inc., an Alcatel company , announced the interoperability between Loquendo's state-of-the-art, multilingual text-to-speech (TTS) technology and the Genesys Voice Platform. Genesys customers, such as Telecom Italia and Sky Italia, are already benefiting from this integration.
  Genesys and Loquendo have successfully performed interoperability testing between the Genesys Voice Platform and Loquendo’s TTS connected through a client-server architecture, based on the quick and easy-to-use remote access features provided by the Loquendo Speech Suite. Through this integration, Genesys TTS applications effortlessly acquire the full potential of Loquendo TTS technology and its advanced f eatures, including Emotional Expressivity, Mixed Language Support and Audio Mixer.
  >> More
• Voiceweb and Loquendo Technology Power The Pythia Taxi Dispatching System in Greece
  June 07, 2005
  Voiceweb, Greece’s premier speech technology integrator and application provider has supported the Pythia Consortium to develop a Taxi Dispatching System leveraging Loquendo’s VoxNauta™ Platform.
  The Pythia taxi dispatching system enables customers to book a taxi over the phone in a matter of seconds. The dispatching system is fully automated and requires no human operator intervention. With the new service, calls will be served in less that 50 seconds, compared to the current 15 minutes waiting time. The percentage of missed calls, as high as 25% during peak hours, will drop dramatically, resulting in a significant revenue increase for taxi companies.
  >> More

EVENTS

• SpeechTEK 2005,
  New York, Marriott Marquis, 1-4 August 2005.
  Visit Loquendo at BOOTH #509.
  
  
• Interspeech Lisboa 2005,
  Lisbon - Portugal, Centro Cultural de Belém, 4-8 September 2005.
• Voice Day 2005,
  Bonn, DE, Alter Bundestag, 20-21 October 2005.