Text-to-Speech Pipeline for Swiss German -- A comparison
This work addresses the challenge of generating high-quality speech for Swiss German dialects, which is an incremental improvement in a domain-specific area.
The authors tackled the problem of synthesizing Swiss German speech by evaluating various Text-to-Speech models, finding that VITS models performed best and achieved previously unachieved quality for different dialects.
In this work, we studied the synthesis of Swiss German speech using different Text-to-Speech (TTS) models. We evaluated the TTS models on three corpora, and we found, that VITS models performed best, hence, using them for further testing. We also introduce a new method to evaluate TTS models by letting the discriminator of a trained vocoder GAN model predict whether a given waveform is human or synthesized. In summary, our best model delivers speech synthesis for different Swiss German dialects with previously unachieved quality.