My Home Made Speech Synthesizer

I was always fascinated with speech synthesizers as a kid. I used to play around with Talking SAM for the Commodore 64 and I even built a hardware speech synthesizer for my Vic-20 using instructions printed in a Popular Mechanics magazine.

A lot of synthesizers append individually recorded phonemes together. But the transition between vowels and consonants are often choppy. Modern synthesizers smooth out that transition by generating the sounds rather than simply playing pre-recorded sounds back to back.

But I always wondered if recording phonemes in pairs and overlapping the shared portions would sound any better. So I wrote a program to do just that and recorded as many pairs as I could with my own voice. The output algorithm is dead simple at the expense of memory. But memory is cheap these days and I figured a library of all possible two-phoneme pairs wasn't going to be much.

Here is the result of my experiment:

Sample

"When in the Course of human events, it becomes necessary for one people to dissolve the political bands which have connected them with another, and to assume among the powers of the earth, the separate and equal station to which the Laws of Nature and of Nature's God entitle them, a decent respect to the opinions of mankind requires that they should declare the causes which impel them to the separation."

speech_sample.wav