I find myself using my smartphone less and less for voice calls and more and more for other types of electronic communication. I’m not nearly as bad as Judie, however, who rarely gets on the phone for actual calls. Still, there are times when we do need to use our smartphones as phones and having the best possible audio quality is important. While attending Mobile World Congress Judie saw the Audience earSmart ES325 Advanced Voice Processor. She was impressed.
The earSmart is the first Advanced Voice Processor that has innovations such as the ability to have simultaneous three-microphone processing, optimization for automatic speech recognition and super WideBand support for voice over IP. It also offers enhanced stereo recording. That translates to improvements of 30 to 55% signal-to-noise ratios when looking at the three microphone performance in noisy environments. That’s incredibly important since it translates into an improvement of 80% over the current two microphone enabled phones we currently use.
The most interesting aspect of this for me is the advancement that comes with this technology with regard to speech recognition. The company points out that the biggest challenge faced by current speech recognition technologies is the failure to recognize spoken words and complete assigned tasks because there is too much ambient noise. The EarSmart uses algorithms that actually isolate voice from ambient sound. The result is better dictation.
Another feature of the earSmart eS325 is Audio Zoom. This lets the mobile device switch between a single speaker in narrator mode and interview mode where the person with the device is actually interviewing another person in seeking to capture both his or her voice and the person being engaged.
This is definitely technology we’re going to want to keep an eye as it is further developed and makes its way into the devices we carry on a daily basis.