Showing posts with label internet speech recognition online technology software nandu. Show all posts
Showing posts with label internet speech recognition online technology software nandu. Show all posts

Sunday, June 21, 2009

On top of the pixel chain



A few years ago, when I was planning to graduate from my 1982 vintage Sears Electra to a digital camera, a 3.2 megapixel Canon was considered state-of-the art. Now, when even DSLRs are fiddling in the 8-megapixel to 12 megapixel range, Canon has come up with a point-and-shoot, sporting a 14.7-megapixel image sensor and promising a shot that can put even professional cameras to shame.

But the Canon IXUS 980 IS is not just about megapixels; it is a complete package. In fact, this compact and sturdy camera is the next best thing to a DSLR. To start with, Canon has improved on most features in its IXUS and Powershot ranges and added a few new ones too. While the 980 doesn’t have a touchscreen, the new dial, which reminds one of the iPod, more than makes up. It helps you shift through the picture styles and change the values with ease on the 2.5-inch LCD. The camera comes with the regular auto, quickshot, manual/ programme/ scene and video modes. But I did find the camera a bit tough to get used to in the manual mode, though it offers shutter speeds up to 1/1600 and two preset apertures.

The 980, however, is not meant for those who will ponder over shutter speeds, for this is an aim-shoot-forget camera all the way. And this is where Canon scores with an easy to use interface and reduced shutter lag. The camera also treads into Photoshop territory by presenting a colour accent mode, which allows you to take away all but one specified colour—however, the option can be unleashed only after a good read of the manual. The widescreen mode is ideal for squeezing in the entire family on a single frame and clicking landscapes. The digitised macro function is great if you like to zoom in on your neighbourhood ant family while the underwater shooting mode can capture your submarine exploits, provided you get a waterproof case along with the camera.

Canon’s night shooting capabilities have only improved, and the 980’s flash assures a bright shot even on a dark night. Moreover, there is the option of the adjusting the flash, so that pictures don’t suffer from burnouts due to excess light.

The playback function now comes with a timeline interface, which lets you skip to specific dates on which the camera has been used. You no longer have to waste time trying to find shots tucked away somewhere between the hundreds you have clicked with the camera. There is also the option of cropping the pictures in playback mode.

While Canon has got most of its features right, the Rs 23,995 price tag spoils the picture for the IXUS 980 IS.

Portable printer

If you are looking for printer to add some sting to your digital camera check out the Canon Pixma iP100, a full-featured, compact, mobile business printer. The IP 100 boasts print speeds of 20 ppm for B&W and 14 ppm for colour and comes with the new 5 Colour ink system. The iP100 also features the Full-photolithography Inkjet Nozzle Engineering (FINE) printhead to provide better quality print.The PictBridge compatible printer can spit out 4 x 6” borderless photo in around 50 seconds.

Friday, June 19, 2009

Let them do the talking


Automatic speech recognition technology is slowly taking over many mundane call center operations

THE next time you hear about the slowdown costing hundreds of call centre jobs around the world, at least a part of it could be the handiwork of Automatic Speech Recognition (ASR), a simple but effective technology that uses computers to identify and analyse spoken words. The technology has been around for a while — even your home computer has it –and is what sets a ringtone when you say the first line of a song or tells you the status of your train as soon as you speak its number into a phone.

In India, the technology has been used extensively over the past couple of years in the telecom, healthcare and automotive sectors. But things are a bit more complex here considering the plethora of regional languages in vogue. But Lattice Bridge Infotech Private Limited (LBIT), the Chennai-based company which pioneered ASR technology in India, has made this very challenge its USP by providing voice-based solutions in 11 Indian languages along with Arabic.

LBIT managing director C Mohan Ram says the ASR and related technologies were initially designed only for English, with regional language support almost non-existent. LBIT, however, changed this with its Simply Speak application for 11 Indian languages. “India has 300 million mobile phone users compared to just 4 million broadband connection, this shows that the spoken word is still supreme here,” says Ram.

He says ASR tries to bridge the communication gap, more prominent in India due to the rampant illiteracy in many parts, by providing services to the common man irrespective of location, time and language. “The application pushes all complexities to the back-end, keeping the front-end interactions simple,” he explains. Simply Speak can now handle live conversations in Hindi, Tamil, Kannada, Telugu, Malayalam, Gujarathi, Marathi, Punjabi, Oriya, Bengali as well as the Indianised English.

Though his company has clients in the BPO industry in the Middle East as well as South Africa, Ram is quick to clarify that the technology is still not good enough to replace call centres. “It can only help make some operations cost-effective. More complex tasks will still need the brain power of people. However, we can make their lives less boring by taking over mundane operations,” adds Ram, whose company has been recognised as among the top 10 centres of excellence in ASR technology across the world. But there is not denying the fact that ASR is cost effective as it can get to work without any requirement for personnel training, especially when faced with human resource or skill shortage.

Ram says his company has achieved accuracy levels of up to 95 per cent for English and between 79 and 92 per cent for the regional languages. The accuracy is measured as FARR (First Attempt Recognition Rate) for various languages and specific application.

However, the local dialects have only complicated things. “Hence, localisation and regionalisation is a continous activity. We spend a lot of time collecting corpus and tuning of various languages,” he adds.

Ram believes the ASR technology has seen a lot of development over the last decade. But work is on to build a larger corpus of words and understand the nuances of localisation and regionalisation.