How to synthesize a sound faster?

[Xiao Z]

I was wondering what I should do to accelerate a speech. We can’t shorten the distance of waveform for it will change the F0. I tried to think that we could cut a piece of waveform but it would make the sound unclear.

How to make a synthesized speech speak faster without changing the pitch?

I want to figure out if it’d be possible to concatenate the piece of sound by a fast-talking provider, or every “standard” sound has its own fixes duration time.

[Simon]

In this topic I noted that we generally avoid performing such signal modifications in unit selection speech synthesis because they degrade the quality. However, speed-up of a synthetic voice is sometimes necessary (e.g., it is required by blind users) and the paper referenced in the above thread compares several ways to do that.

In older diphone synthesis, it was necessary to manipulate duration and F0 independently, and there are several ways to do that. You can try TD-PSOLA for yourself in Praat.

[Author]

Posts