- 19 May 2004 10:37
ScanSoft Unveils OpenSpeech Recognizer 3.0, Sets New Industry Benchmark for Speech Recognition Engines
AUSTRALIA, Sydney, 19 May, 2004 – ScanSoft, Inc. (Nasdaq: SSFT), the global leader of speech and imaging solutions, today introduced OpenSpeech™ Recognizer 3.0, establishing a new industry benchmark for speech recognition software and marking the first major product developed post-merger by the SpeechWorks Division of ScanSoft.
OpenSpeech Recognizer 3.0 combines advanced features derived from the division’s existing speech recognition engines as well as new capabilities created by its extensive research and development team. Featuring the industry’s broadest language portfolio and optimised for superior application performance, OpenSpeech Recognizer is ideal for implementing global speech strategies at enterprise and telecommunications companies worldwide.
“The SpeechWorks division of ScanSoft has never been in a better position to bring its full speech capabilities to bear on the global enterprise and telecom market,” said Daniel Hong, analyst for Voice Business at Datamonitor, a leading research firm. “SpeechWorks has further advanced its strategic relationships with standards-based platform providers by providing them with a truly global and feature-rich speech recogniser to develop and deploy customer self-service solutions worldwide. All of these assets, combined with its global resources and expert professional services team, place the SpeechWorks division in an elevated position in today’s speech market.”
Companies around the world trust SpeechWorks to develop and deploy their speech strategies. With the greatest market share position in core speech technologies, applications and services, SpeechWorks solutions successfully automate more than five billion telephone conversations annually. Its ability to develop and deploy applications on all major speech platforms and devices in multiple languages has made it the preferred speech provider of the Fortune 100.
“The introduction of OpenSpeech Recognizer 3.0 represents a generational leap in capabilities on a product level – but also signals the beginning of a number of exciting new product innovations that leverage the amalgamation of a host of superior technologies,” said Steve Chambers, president of SpeechWorks, a division of ScanSoft. “With the support of our global partner network, we deliver these advancements to our customers, who ultimately benefit through higher caller satisfaction and an accelerated return on investment.”
Optimised for Superior Application Performance
Enterprise and carrier organisations around the world are implementing speech applications as part of their call center and workforce management solutions to increase call automation and reduce costs while increasing caller satisfaction. OpenSpeech Recognizer 3.0 is tuned for the most challenging and fastest growing speech applications in today’s market, such as auto-attendant, automated directory assistance and natural language customer self-service. It incorporates enhancements to support the specific recognition tasks often employed in these applications:
Enhanced Natural Language Input: SpeakFreely™ natural language capabilities enable applications such as call routing or customer self-service to respond precisely to callers’ naturally phrased requests. SpeakFreely grammars are built automatically from textual examples of what a caller might say along with the meaning of each response. SpeakFreely can shift complex grammar development from speech specialists into the hands of application developers.
Expanded Support for Proper Names: OpenSpeech Recognizer 3.0 includes an expanded pronunciation dictionary in each language pack that provides comprehensive coverage of proper names local to that language. Ideal for applications such as Auto-Attendants, this feature boosts recognition accuracy while simplifying vocabulary maintenance.
Improved Support for Large Menu Lists: A new grammar file format accelerates compilation of large menu lists commonly used in automated Directory Assistance applications. This new feature speeds the preparation of updated grammars, thereby allowing more timely updates for more accurate listings, resulting in higher automation rates.
Advanced Tuning Tools & Reporting: An updated OpenSpeech™ Insight tool is included to assist with the development and maintenance of speech applications. The latest version offers increased support for analysing high call volume speech deployments that require distributed call handling systems. With over 50 customisable reports, developers can easily determine which parts of a speech application may need attention to reach higher transaction completion rates and higher caller satisfaction.
The Industry’s Broadest Language Portfolio
OpenSpeech Recognizer 3.0 delivers the industry’s broadest language coverage through a global network of platform partners to serve organisations around the world. Customers and partners can deploy speech applications in virtually any market using OpenSpeech Recognizer’s global capabilities, including the following:
Unmatched language coverage: OpenSpeech Recognizer 3.0 provides speech recognition in 44 languages and dialects, more than any other speech recognition product available today. Additional languages can be developed on a custom basis to meet the needs of specific applications.
Multilingual capabilities: OpenSpeech Recognizer 3.0 offers full multilingual capabilities that allow any combination of languages to be mixed within a single utterance. This feature is valuable in bilingual markets where callers often switch between languages in a single response. For example, in Canada it might be used to seamlessly recognise responses combining English and French.
– Adaptability: Patented LEARN capabilities continually and automatically adapt the recogniser to each specific deployment. LEARN quickly adjusts acoustic models to local dialects, regional accents and telephony channel characteristics. The net result is measurably improved recognition accuracy without any additional effort, even if caller demographics shift over time.
Builds on Field-Proven Speech Technologies
OpenSpeech Recognizer 3.0 creates a unique best-of-breed design, drawing on carefully selected algorithms, development techniques, and components successfully employed in the SpeechPearl® and OpenSpeech Recognizer product lines. This approach delivers a single, feature-rich speech recognition product to service the global speech recognition market, lowering development, sales and support costs for telephony platform developers. Enhanced features of OpenSpeech Recognizer 3.0 include the following:
Improved Accuracy: Core technology improvements have reduced recognition error rates by an average of 25% on a variety of tasks compared to OpenSpeech Recognizer 2.0. Fewer recognition errors lead to greater caller satisfaction, higher call completion rates and a faster return on investment.
Scalability and Memory Reduction: OpenSpeech Recognizer 3.0 incorporates techniques such as Finite State Transducers (FST) to reduce memory and CPU consumption without compromising recognition accuracy, increasing channel density and so lowering overall system cost. Savings of 90% can be realised for large grammars.
Improved Confidence Scoring: OpenSpeech Recognizer 3.0 features new algorithms for more accurate confidence scoring, reducing the need to prompt for confirmation of inconclusive recognition results. This reduces individual call times to expand call handling capacity while raising caller satisfaction.
Flexible Deployment Architecture: OpenSpeech Recognizer 3.0 is available in all-in-one and client-server architectures sharing a common API that is backwards compatible with OpenSpeech Recognizer 2.0. In addition, support for MRCP is available from the newly updated SpeechWorks MediaServer 3.0, which also includes Speechify® text-to-speech, providing customers with more deployment options.
Pricing and Availability OpenSpeech Recognizer 3.0 will be generally available on May 31, 2004 for Microsoft Windows 2000 & Windows 2003, Red Hat Linux 7.2 and Red Hat Advanced Server 2.1 operating systems. Updated support for SPARC Solaris 8 client will be available in July. For pricing and additional information, contact your ScanSoft sales representative.
About the SpeechWorks Division of ScanSoft
SpeechWorks is the most trusted name in speech. Through its global partner network, SpeechWorks delivers field-proven applications that revolutionise the way people interact. Today, thousands of companies and millions of users around the world depend on SpeechWorks® solutions from ScanSoft to deliver vital business information and simplify every day life. For information, please visit http://www.scansoft.com/speech.
About ScanSoft, Inc.
ScanSoft, Inc. (Nasdaq: SSFT) is the global leader of speech and imaging solutions that are used to automate a wide range of manual processes - saving time, increasing worker productivity and improving customer service. For more information regarding ScanSoft products and technologies, please visit www.ScanSoft.com.
ScanSoft, SpeechWorks, SpeechPearl, SpeakFreely, OpenSpeech, Speechify and the ScanSoft logo are registered trademarks or trademarks of ScanSoft, Inc. and/or its subsidiaries in the United States and other countries. All other company or product names may be the trademarks of their respective owners.