Vicorp Announces GA of xMP 4.4 Service Creation Environment

Vicorp has announced General Availability of version 4.4 of its award-winning service creation environment (SCE) toolset "xMP". The tools allow graphical creation of complex speech recognition applications, as well as run-time management of dynamic voice applications and "virtual IVR" farms and deployment of multi-lingual and multi-brand services.

Version 4.4, in particular, provides improved support for load balancing and call routing, as well as greater flexibility in the handling of detailed grammar properties and concatenated audio.

SRI International Receives Patent for Voice-Based Search Technology

SRI International, an independent, nonprofit research and development organization, today announced that it has been issued a second U.S. patent for its voice-to-database (V2DB) technology that enables one-step, voice-based access to items in vast, multimillion-record databases.
SRI's one-step approach allows users to receive accurate information using a natural interaction style, saving time and eliminating tedious and lengthy prompt menus used in some consumer device and call center user interfaces.
SRI's technology can work with currently available speech recognition systems, enabling fast access to frequently searched items such as contacts, song and ringtone downloads, addresses, driving directions, and catalog items [click heading for more]

Lightning-speed demonstration of building speech recognition application with service creation tool


This quick demonstration shows the main concepts of the Vicorp xMP Director service creation tool by building a very simple call flow, which includes an agent transfer and database look-up. No coding is required, and prompts can be configured at a later date (by the VUI designer) in the xMP Studio tool.


The Coming Wave of Gadgets That Listen and Obey

INNOVATION usually needs time to steep. Time to turn the idea into something tangible, time to get it to market, time for people to decide they accept it. Speech recognition technology has steeped for a long time: Mike Phillips remembers that in the 1980s, when he was a Carnegie Mellon graduate student trying to develop rudimentary speech recognition systems, “it seemed almost impossible.”
Now, devices that incorporate speech recognition are starting to hit the mass market, thanks to entrepreneurs like Mr. Phillips. [click heading for more]

Open Source Speech Recognition arrives

The first version of the open source speech recognition suite simon has been released. It uses the Julius large vocabulary continuous speech recognition to do the actual recognition and the HTK toolkit to maintain the language model. These components are united under an easy-to-use graphical user interface. Simon can import dictionaries directly from wiktionary (a subproject of wikipedia) or from files formated in the HADIFIX- or HTK format and grammar structures directly from personal texts. It also provides means to train the language model with new samples and add new words." [click heading for more]

Voice Mash-ups – Imagination is the biggest barrier

Voice as an interface is overlooked. The phone is ubiquitous. Everyone knows how to use them – and how to interact with automated voice applications. As well applications like speech recognition (ASR) and Text to Speech (TTS) are robust enough to make voice a reliable option for both control and data delivery for any application. Combine this with web development approaches, which have proven architectures to deliver a seamless user experience by coordinated multiple services and opportunity for new voice applications is apparent.

Still all development depends on having both users and a business case. By using data from multiple sources, delivering them through existing services and by focusing on a relatively small feature set mash-ups make it easy to solve issues that might be ignored with other paradigms. [click heading for more]

Microsoft applies to patent "answering machine detection using speech recognition"

The US system of patents is patently (pun intended) very different from the UK
one. It seems to me that Microsoft's latest patent application is decidely
obvious, and is not-very-far-removed from techniques already in use for
outbound dialling systems; basically it amounts to a "liveness" test of what's
on the other end of phone... which is all very well until I implement a
speech-enabled voicemail application that answers back :-) The abstract
follows:

An answering machine detection module is used to determine whether a call
recipient is an actual person or an answering machine. The answering machine
detection module includes a speech recognizer and a call analysis module. The
speech recognizer receives an audible response of the call recipient to a call.
The speech recognizer processes the audible response and provides an output
indicative of recognized speech. The call analysis module processes the output
of the speech recognizer to generate an output indicative of whether the call
recipient is a person or an answering machine.[
click heading for more]

Telephonetics VIP uses speech recognition to reduce wasted resource with Remind+

Telephonetics VIP has released an automated notification solution based on speech recognition technology. The automation specialist has released the Beta version of Remind+, a solution that enables organisations to contact people and remind them they have an appointment in the near future and logs their spoken responses, enabling unused slots to be speedily reallocated.

Missed appointments can cost organisations millions of pounds each year. For example, in the NHS, 10% of appointments set each year are not attended resulting in an estimated annual loss of over £600 million, an average of £130 per missed appointment. It is worth noting these costs are not limited to the public sector and Remind+ is equally productive for organisations in the private sector such as legal, finance and private health professions. [click heading for more]

Envox 7 Wins TMC's Internet Telephony Magazine 2007 Product of the Year Award

Envox Worldwide today announced that Envox 7,the company's open, standards-based communications development platform,has been selected by Technology Marketing Corporation's InternetTelephony magazine as a 2007 Product of the Year. Envox 7 is an open, standards-based platform with integratedapplication development and management components that significantly reducethe time, cost and complexity of deploying voice and IP communicationssolutions. Envox 7 combines comprehensive support for traditional voicecommunication with the industry's most complete support for IPcommunication, including IP telephony, video messaging, SMS, and e-mail. [click heading for more]