AdaSpeech: Adaptive Text to Speech for Custom Voice

Contents

Audio Samples

Adaptation voice on LibriTTS, VCTK and LJSpeech

VCTK speaker : Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob.

VCTK speaker : The Greeks used to imagine that it was a sign from the gods to foretell war or heavy rain.

LJSpeech speaker : Especially as no more time is occupied or cost incurred in casting setting or printing beautiful letters.

LJSpeech speaker : Printing in the only sense with which we are at present concerned differs from most if not from all the arts and crafts represented in the exhibition.

Libritts speaker : And so, howsoever reluctantly, she had gone.

Libritts speaker : All that I am doing is to use its logical tenability as a help in the analysis of what occurs when we remember.

Ablation Studies

Audios of Ablation Study on VCTK

VCTK speaker : There is , according to legend, a boiling pot of gold at one end.

VCTK speaker : Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob.

Audios of Utterance-level Visualization Analysis

Pink Point in Brown Circle

Blue Point in Brown Circle

Audios of Finetune CLN and Finetune Other Decoder Parameters

VCTK speaker : Ask her to bring these things with her from the store.

Audios of Varying Adaptation Data on AdaSpeech

LJSpeech speaker : especially as no more time is occupied or cost incurred in casting setting or printing beautiful letters.

VCTK speaker : Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob.

Demo Audio for ICLR 2021 Response

[speaker embedding with the utterance-level vector extracted from a different speaker] for AnonReviewer5

VCTK speaker : Ask her to bring these things with her from the store.

VCTK speaker : She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.

[exp1] for AnonReviewer5

VCTK speaker : Ask her to bring these things with her from the store.

VCTK speaker : We also need a small plastic snake and a big toy frog for the kids.

[exp2] for AnonReviewer5

Finetune DataSet

VCTK speaker : Ask her to bring these things with her from the store.

VCTK speaker : When the sunlight strikes raindrops in the air, they act as a prism and form a rainbow.

[exp3] for AnonReviewer5

VCTK speaker : Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob.

Libritts speaker : It is not logically necessary to the existence of a memory belief that the event remembered should have occurred, or even that the past should have existed at all.

[Some speakers don't sound so good] for AnonReviewer2

VCTK speaker : People look, but no one ever finds it.

VCTK speaker : Please call Stella.

VCTK speaker : Throughout the centuries people have explained the rainbow in various ways.

VCTK speaker : Some have accepted it as a miracle without physical explanation.