Need for MRCP

Well, I work for a company Ozonetel (www.ozonetel.com) and we specialize in voice products. We work a lot with Asterisk and in almost all projects I realized that as a telephony platform, Asterisk is great. It allows you to make and receive calls. But still there are a lot of loose edges and a lot of functionalities can be added. Almost every project now-a-days deals with speech. Everyone wants speech recognition and Text to speech. And that is where Asterisk is lagging a little bit. There are hacks to deal with TTS(through Festival Cepstral etc) and speech recognition (sphinx etc), but there is no standard solution.
Enter MRCP. If a plug in or module for MRCP existed for asterisk then we immediately get connected to many Speech servers like Nuance, Telisma etc. So I started searching around for a solution. After all I am a very good programmer and I embody the most important trait of a programmer, laziness :) So if someone has already built it, then why bother :).
But surprise of surprises, I could not find any solutions. Then I started to search for atleast MRCP solutions so that I could integrate. Even there, I could not find any stable solutions. Just as I was thinking of creating my own MRCP solution,luckily I found a project which was showing some good activity. I tried considering speechforge and zanzibar as I am mainly a Java guy, but their development was stagnant.On the other hand, unimrcp ( www.unimrcp.com) was being developed actively, so I checked out the code and played around with it. It installed perfectly, though I had to modify the configure parameters for Ubuntu (both sofia sip and apache apr were installed in seperate locations) and it worked perfectly. The code was also very well written and the design was top notch. And most importantly, the main developer, Arsen, responded to the queries on a real time basis.I knew we had a winner.
Next post we will look at how I implemented the solution.