Every once in a while you find a company that has the odds stacked against them. TravellingWave, which occupies a three-room office just outside of downtown Seattle, has just five employees, including the founders, and is in the highly competitive space of trying to figure out how to use voice recognition, which has historically been plagued by inaccuracies, as a way to input information into small devices. To boot, the company’s list of competitors includes giants such as Microsoft (NSDQ: MSFT) and IBM, and public companies like Nuance Communications. Founder and CEO Ashwin Rao said it perfectly: “We are in a small niche that’s a crowded market. It’s dumb unless we have a solid differentiator.”

As a company with one year under its belt and a couple of unofficial years, Rao gave me a sneak peak of an announcement it plans to release today that may just be the thing that can put the company on the map. To date, it’s big differentiator has been combining voice-recognition with some texting. For instance, when sending an SMS, a user would first speak the word “hello,” and then hit the “h” key, which would bump up the software’s accuracy. If a person came a long a word that proved more difficult, they would keep typing letters of the word until it was recognized. With one letter, the accuracy increases to 90 percent, with two letters, it’s 95 percent, and with three it becomes 99 percent, they claim. In addition, they say people input three times faster with four times less key presses. But the big issue TravellingWave faced was background noise and clarity of the person speaking. The phone is in “always listening” mode, which means that a person doesn’t have to press and hold a key when talking into it, but it also means a lot of noise can be picked up. The solution they came up with is the speech processing algorithm they call RAGs, which extracts a person’s voice while removing extra noise and clicks, so a voice can be recognized in even the toughest environments. TravellingWave is currently in trials with multiple mobile phone manufacturers and carriers for their software, which they call VoicePredict. A beta will be released in the second half of the year as a publicly available download for Windows Mobile.

In addition to coming up with RAGs, TravellingWave is also announcing that it is appointing Todd Achilles, former general manager of HTC-Americas, and executive director of handsets for T-Mobile USA, to its advisory board. The company has been funded through a small seed round from angel investors, including Jim Judson (formerly with McCaw Cellular); Bill Miller (a former venture capitalist), Geoff Entress (a VC) and Colin Wong (formerly with Google); and a couple of National Science Foundation grants. In a release, Achilles said: “I have seen many approaches to solving the mobile speech-to-text challenge, all of which have been frustratingly inconsistent. The TravellingWave approach flips the problem on its head and provides a major leap forward in the user experience for mobile consumers.”

• TravellingWave Launches, Announces Funding For Predictive Speech To Text