Terre Haute company to test dictation software

InfraWare Inc., a medical transcription software company, announced Thursday it soon will begin beta testing its new dictation recognition engine aimed at increasing the speed and reducing the cost per line of medical transcription through intelligent back-end automation.The Terre Haute-based software developer and transcription ASP provider will marry its existing InfraWare 360 transcription speech recognition platform and its newly developed artificial intelligence engine to generate more accurate and less expensive first-draft text versions of physician audio dictations. Of the $1.2 million project budget, $871,000 was supplied by a grant from the state’s 21st Century Research and Technology Fund. [click heading for more]

Tellme and Aspect Software to Deliver Innovative Solution to Contact Center Customers

Tellme(R), a Microsoft(R) subsidiary, and Aspect Software today announced anagreement to bring together the Aspect unified contact center solution and services with Tellme's proven voice services platform to deliver a flexible, cost effective joint contact center solution. The agreement between Tellme and Aspect expands on the strategic, multi-year alliance that Aspectand Microsoft made earlier this year to deliver contact center solutions withdeeper unified communications capabilities. [click heading for more]

Google audio search graduates to lab project

Google has elevated the profile of its attempt to make videos searchable through speech recognition technology, a move that portends a potentially more financially successful YouTube division.
The speech recognition technology was used in an online application that let people search political speeches launched in July, and now the Gaudi (Google Audio Indexing) project has an official interface at Google Labs. [click heading for more]

Tellme Delivers Spanish Speech Solution for Domino's

For Domino’s Pizza, speech rec has proven to be a sizzling way to manage calls and serve customers. Domino’s now wanted to extend the speech rec capabilities to its Spanish speaking customers, a growing and underserved market. It had found that multilingual staffing was inconsistent across stores, making the Spanish ordering experience inconsistent and sometimes impossible. While customers could use the Tellme-provided service, which would connect them to a Spanish-speaking agent, many of them would hang up because Tellme would greet them in English. [click heading for more]

Promptu Unveils High Accuracy Voice-to-Text Dictation for Mobile Phones at CTIA

Promptu Systems Corporation unveiled today at the CTIA trade event in San Francisco a new and highly accurate voice dictation system. Using the company's proprietary Client Server Speech Recognition (CSSR(TM)) technology, the system converts a user's fluent, natural speech almost instantly into text. Suggested as a safer, more convenient text input method than the limited 12-button keypad of typical mobile handsets, the system is targeted at SMS, email and social networking applications. [click heading for more]

Yap Taps Caringo to Provide Content Storage Infrastructure for Next Generation Voice-to-Text Platform

Caringo, Inc. announced today that Yap Inc. has selected the company to provide the content storage infrastructure for Yap's next-generation mobile speech-to-text platform.
Yap will utilize Caringo's CAStor(TM) content storage software built on third-generation content addressable storage (CAS) technology to create a high-performance storage infrastructure with virtually unlimited scalability to support audio and text content derived from Yap's innovative Automatic Speech Recognition cluster. [click heading for more]

Vicorp strengthens its relationship with the US market

UK based Vicorp is delighted to announce its partnership with Newfound Communications, a US based speech solutions provider. Not only does the partnership increase Vicorp presence in the US market, but also broadens their portfolio.

Vicorp and Newfound Communications are established in their own countries, but this partnership presents both companies with exciting opportunities to extend their reach into the US and Europe.

"Our companies share the same desire to help organisations and developers deliver superior features, which enhance over-the-phone contact centre experiences for the end caller," says Craig Ashmole, Vicorp VP of Alliances and New Business.

"Newfound Communications have enabled us to extend our portfolio to offer assisted outbound IVR, voice recording and enriched self-service branding. This capability takes us ever closer to our mission to provide 100% call resolution for our customers. We are excited by the potential of this partnership."

Both Vicorp's and Newfound Communications' technology is XML based and complements one another for a richer integrated offering. Vicorp's service creation and execution environment, xMP, in conjunction with Newfound Communications' products including call recording, media mixer and outbound dialler all contribute to a stronger portfolio for both companies. In using Vicorp service creation and execution environment, xMP, Newfound Communications will now be able to pass onto their customers benefits such as editable and re-usable component technology. [click heading for more]

Eckoh wins multi-million pound contract from global financial services company

Eckoh plc, the UK’s largest provider of hosted speech recognition services, has signed a three year multi-million pound contract with a global financial services company to provide an automated telephony self-service platform for handling customer enquiries across Europe.
The contract is forecast to start generating revenue by the fourth quarter of the current financial year, and to reach full run rate well in excess of £1 million per annum in the first half of the next financial year.
As stated in the preliminary results announcement on 4 August 2008, Eckoh have been working with BT to create a network which will allow calls to be delivered from all major European territories to Eckoh’s call processing platform in the UK. Through the agreement this client will be the first to utilise the new capability and it underlines Eckoh’s ability to now provide cost-effective hosting facilities on a pan-European basis to major global businesses. [click heading for more]

Aterisk: VXI* 3.1 final released!

The final VXI* VoiceXML browser 3.1 “late summer” ref. 2008-09-01 32bit is now released! In few days the same package for 64bit will be available too. These new release is suitable for production platforms running with all lastest Asterisk 1.4 kernels.

New features added:
add: additional properties for the TextToVideo
add: Specific video URL in the accounts
add: Video detection
add: Counters (PEAK, DENIED, SPEECHS)
add: Set VXML_ERROR if the session cannot be open (content the cause)
add: End date to the session dump
add: Use Number (calledif)) to identify the account
add: Option mute to openvxi
add: CLI admin commands
add: alias mimitype video/3gp
add: VXML() asterisk function to get/set parameters
add: Porting for Asterisk 1.2
add: Priority configuration
add: Sessions dump
add: CDRupdate parameter
add: Asterisk vxml application dates
add: Add the dial: transfer prefix
add: CDR updates at the end of the VoiceXML session
add: .alaw and .ulaw formats for the TTS
add: ASR automatic allocation
add: speech configuration for the accounts
add: Object property to get internal properties values
add: Configuration of DTMF controls
Modifications:
mod: Disable SIGPIPE generation
mod: Open sessions locks
mod: support Jsession (java sessions)
mod: Start/stop script (without safe_openvxi)
mod: Disable log Stdout by default
mod: Remove direct chan access
mod: vxml show application
mod: Correction in the offset object
mod: Small correction for CLI commands
mod: Correction to use the MP3Player application
mod: Correction to support exec: in the transfer [click heading for more]

Speech technology improves service at council

Warwickshire County Council employees have entered their names into a new speech recognition system, to automatically direct customers to the person they want to speak to.

The speech technology, by Macfarlane, will ask incoming customer calls for the name of the person they wish to speak to.

The system will then match them to names contained in its database, and route calls through to the correct telephone extensions. [click heading for more]