When you speak to someone, they don’t just recognize what you say: they recognize who you are. WhisperID will let computers do that, too, figuring out who you are by the way you sound.
- Home PC Security. In your home, Speaker Identification will make it easier for you to log into your computer, just by saying «Log me in!»
- Office PC Security. In your office, Speaker ID can add an extra level of protection to your computer, making it even harder for someone to break in — not only will they need your password, they will have to be able to do a great job of imitating your voice.
- Home Electronics. In the more distant future, when your home is electronic (see the Easy Living Project), when you say «Computer, turn on the radio», it won’t just turn the radio on, it will recognize who you are, and set it to your favorite station. When your child tells the house «Computer, turn the thermostat up to 85» the computer will recognize his voice, and refuse to do it.)
How Speaker ID works. Each person’s voice is different. Some sounds, like «s», sound about the same no matter who says them, but other sounds, like vowels, tend to differ a lot from person to person. We use a special way of representing sound, the cepstrum, that captures lots of information, including the characteristic way you pronounce your vowels. Of course, someone could imitate the way you talk; fortunately, the cepstrum also captures certain fundamental characteristics of voices that are impossible to change. For instance, the length of your vocal tract — the place where sound is produced in your body — cannot be changed, and different length vocal tracts tend to produce cepstra with different characteristics. By identifying both the way you talk, and the way your body produces sound, WhisperID can do a great job of figuring out who you are.