Some straightforward, but effective techniques to improve the performance of speech synthesis using simple feedforward networks.

Measures the relative contributions of the key differences in the regression model, state vs. frame predictions, and separate vs. combined stream predictions.

DCTTS is comparable to Tacotron, but is faster because it uses non-recurrent architectures for the encoder and decoder.

FastSpeech 2 improves over FastSpeech by not requiring a complicated teacher-student training regime, but instead being trained directly on the data. It is very similar to FastPitch 2, which was released around the same by different authors.

The term “trajectory tiling” means that trajectories from a statistical model (HMMs in this case) are not input to a vocoder, but are “covered over” or “tiled” with waveform fragments.

Another way to combine waveform concatenation and SPSS is to alternate between waveform fragments and vocoder-generated waveforms.

Although standard speech quality measures such as PESQ do not work well for synthetic speech, specially constructed methods do work to some extent.

Multi-dimensional scaling is a way to uncover the different perceptual dimensions that listeners use, when rating synthetic speech.

A distillation of the key findings of the first 10 years of the Blizzard Challenge.

Of purely historical interest, this is an example of a system using a heterogeneous unit type inventory, developed shortly before Hunt & Black published their influential paper.