Higher speaking rates

[E Hermann]

How do TTS systems support higher speaking rates? Is it usually just a (pitch-preserving) speedup of the waveform or are there also efforts to model contractions and other related changes in the frond end?

E.g. in German, glottal stops are commonly inserted before words starting with a vowel and other syllables with an initial stressed vowel, but this happens less and less frequently at higher speaking rates, so for TTS it would also make sense to drop glottal stops from the linguistic specification in that case.

[Simon]

In unit selection (i.e., concatenative) speech synthesis, we generally avoid making any modifications to the recorded speech, because they will introduce artefacts and so degrade naturalness. It’s much easier to vary speaking rate in statistical parametric synthesis.

To read our recent research in this area, try

Cassia Valentini-Botinhao, Markus Toman, Michael Pucher, Dietmar Schabus, and Junichi Yamagishi. “Intelligibility of time-compressed synthetic speech: Compression method and speaking style” in Speech Communication, Volume 74, Nov 2015, pp 52–64. DOI: http://dx.doi.org/10.1016/j.specom.2015.09.002

One finding is that linear time compression of normal speech is the best strategy. This is not what happens in natural speech though. As you point out, natural fast speech does indeed involve more and more deletions, but these seem to harm intelligibility and so we must conclude they are done to benefit the speaker (less effort) and not the listener.

[Simon]

It’s also worth noting that certain users need exceptionally high speaking rates. Blind computer programmers are one example.

Some people may still use formant synthesis, depending on personal preference.

[Author]

Posts