Fitting New Speakers Based on a Short Untranscribed Sample
This addresses the challenge of speaker adaptation in TTS for applications requiring quick voice cloning, though it appears incremental as it builds on existing learning-based methods.
The paper tackles the problem of adapting text-to-speech systems to new speakers using only a short untranscribed audio sample, achieving greatly improved performance even with very short samples.
Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that is designed to capture a new speaker from a short untranscribed audio sample. This is done by employing an additional network that given an audio sample, places the speaker in the embedding space. This network is trained as part of the speech synthesis system using various consistency losses. Our results demonstrate a greatly improved performance on both the dataset speakers, and, more importantly, when fitting new voices, even from very short samples.