Multiple voices dataset

[JRMeyer]

>>> Daksh_Varshneya
[May 22, 2020, 8:23am]

Hi, slash
I am trying to fine-tune TTS models further. For that purpose, I am
trying to collect a dataset where hopefully the audio samples are more
expressive in nature. It is tough to collect a dataset in only one voice
such as LJSpeech dataset. If I collect some good quality dataset but
with multiple different voices spread across the audio samples, will it
be difficult to train the model on this dataset? I can make sure that
one audio sample has only one distinct voice. But across samples, this
may not hold true. slash
Any suggestions?

[This is an archived TTS discussion thread from discourse.mozilla.org/t/multiple-voices-dataset]

[JRMeyer]

>>> georroussos
[May 22, 2020, 10:24am]

Are you looking for multispeaker datasets? There's many. You can go with
LibriTTS. Since it comprises of audiobooks, it tends to be expressive.

[Archived Post]

[JRMeyer]

>>> Daksh_Varshneya
[May 22, 2020, 10:49am]

Yes, but would I be able to train on a multispeaker dataset? How does
the model learn a final voice to speak in? Does the model take a speaker
ID as well as input in that case?

[Archived Post]

[JRMeyer]

>>> georroussos
[May 22, 2020, 11:04am]

That is the point, that it learns to speak in many voices.

If you choose single speaker TTS, it is one voice you need and a
multispeaker dataset will not work. If you choose multispeaker, you
train using speaker embeddings, so then you get many voices. If you are
looking for expressiveness, I would recommend
's fork, which implements
GST with Taco2, combined with LibriTTS. You can get good results.

[Archived Post]