|
|
Interactive Voice Response
This section of our technical library presents information and documentation relating to IVR and interactive voice response software as well as automatic call answering solutions.
Business phone systems and toll free answering systems (generally 800 numbers and their equivalent) are very popular for service and sales organizations, allowing customers and prospects to call your organization anywhere in the country.
Our PACER and Wizard IVR systems add another dimension to our call center phone system solutions. An Interactive Voice Response (IVR) processes inbound phone calls, plays recorded messages including information extracted from databases and the internet, and potentially routes calls to either in-house service agents or transfers the caller to an outside extension.
Speech recognition software is ready
by Sadagopan, fecolumnists.expressindia.com
ScanSoft announced Version 8.0 of its award-winning speech recognition software, ‘Naturally Speaking’ in November 2004. Interestingly, this was a release after nearly two years. With this release ‘Nat Speak’, as this software is widely known, has worked with a laser- shop focus on accuracy, instead of adding some fancy features as is characteristic of many software releases. This has improved recognition accuracy to 98.5%. This means practically all the words you speak would be recognised correctly and you can “dictate” to a machine instead of a stenographer. Since a computer (desktop or laptop) is available to you most of the time, you can dictate any time and not “hold” your thoughts until the next working day, when you get access to the stenographer.
Speech recognition has been heavily researched for decades. But one had to wait for ‘mature’ products all these years.
- It took several years for us to understand the natural language and human speech, though early AI (artificial intelligence) researchers in the ’60s thought that machines can “win over” many hurdles in just a decade.
- Second, speech recognition is ‘computer-intensive’, needing significant processing power; most of the early experiments were run in the ‘background’, typically on an expensive mainframe computer. It’s only in recent years that speech recognition has come to end-users, thanks to powerful desktop and laptop computers with processors running at clock speeds of 1+ GHz, and RAM sizes of 256+ MB.
- Third, recognition accuracy of 95% range, though it appears excellent, is “no good”; though the users save time in ‘keying in’ 95% of the text, correcting 5% of the text can be so unnerving that the 95% savings loses its charm. Imagine dictating to a stenographer who makes 25 mistakes in a five- minute dictation! (We typically speak 100+ words per minute).
What does it mean to you? You can start using ‘Nat Speak’ type of speech recognition software routinely in your day-to-day life creating your documents, ‘speaking out’ your e-mails, responding to your e-mails, and ‘speaking out’ most of the documents that are processed by MS Windows.
- This can dramatically increase your productivity if you write a lot, irrespective of your profession—doctor, lawyer, writer, journalist, professor, software documentation expert, corporate communications person or even mom and pop who send lots of e-mail to their children and grand- children. Even a fast typist typically types 40 words per minute, but you can easily speak 120 words per minute.
You protect yourself from repetitive strain injury arising out of excessive typing that is associated with heavy e-mail and PC users.
There are other products from competing vendors. ‘Via Voice’ from IBM is an equally good product. Interest-ingly, many vendors in this arena have either merged their operations with others or closed down, leaving ScanSoft’s ‘Nat Speak’ and IBM’s ‘Via Voice’ as the key players in the market.
As of now, mature products are available only for MS Windows; you have to wait for products in the Linux world to mature. Microsoft has been bundling ‘Speech’ with its MS Office product for years; it is still not mature enough for end-users. The scene might change dramatically if their speech engine acquires recognition accuracies of ‘Nat Speak’.
What are the downsides? Speech recognition software is not inexpensive; it costs about $200. You need to invest quality time in ‘training’ the software when you start using it for the first time. It takes several minutes to ‘train’ the software with YOUR voice. These are NOT ‘word recognition’ systems but ‘continuous speech’ recognition systems that work well if you speak continuously.
If you are NOT used to speaking naturally or dictating to a stenographer, you will NOT find speech recognition software very useful. These softwares are very useful if you have thought through the text and ‘speak out’; not if you are the type who reads e-mail hurriedly, types answers in monosyllables, looks at them, corrects them and presses the ‘send’ button of MS Outlook!
Speech recognition software availability is limited to English (and other foreign languages) at this point; a number of products for Indian languages are under development. Hopefully, they will mature in the next couple of years.
The author is director of Indian Institute of Information Technology, Bangalore. These are his personal views
Wizard Simplifies Development
DSC provides IVR software including our IVR wizard development tool for creating interactive voice response applications.
Our IVR software lets you increase IVR development productivity by providing a visual development environment. IVR applications can be defined in minutes using this sophisticated, yet easy to use development tool.
DSC also has available a comprehensive IVR software library known as our IVR Wizard Software Development Kit. This optional package is available for programmers and systems adminstrators who wish to manage IVR programs fromLinux IVR, Unix, or Windows IVR operating environments.
Data collected by your phone ACD (Automatic Call Distribution) or IVR (Interactive Voice Response) systems can be passed to your existing PC, Unix or Web applications through our phone software.
The PACER predictive dialer can automatically call your customers and pass only connected calls to your agents. With our computer telephony software, your telephone and computer work together to provide cost-saving benefits.
|
