MAE-VC

MAE-VC: Voice Conversion Using Learnable Similarity-Guided Masked Autoencoder

Compared with other methods

VCTK

  1. F2F, Our dispute is with the company, not the travelling public.
  2. F2M, I feel we might now have the foundations to go forward.
  3. M2F, She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.
  4. M2M, The actual primary rainbow observed is said to be the effect of super-imposition of a number of bows.
Source Target ADAINVC AGAINVC MediumVC FragmentVC MAE-VC

VCC2020

  1. F2F, Their solution requires development of the human capacity for social interest.
  2. F2M, Income rose zero point four percent last month.
  3. M2F, There is a connection between all of this.
  4. M2M, The problems I mentioned are not insurmountable.
Source Target ADAINVC AGAINVC MediumVC FragmentVC MAE-VC

LibriSpeech

  1. F2F, Turning the first corner he came to, and the next and the next, he stepped into a mews, the court of which seemed empty, and slipped behind the gate.
  2. F2M, In India it is usually made with chicken, but any kind of meat does nicely.
  3. M2F, All this against which he now inveighed so bitterly was but a necessary stage in the shaping of his odd destiny.
  4. M2M, And the subordinate care of justice and the revenue was delegated to seven consulars, three correctors, and five presidents, who governed the fifteen regions of Italy according to the principles, and even the forms, of Roman jurisprudence.
Source Target ADAINVC AGAINVC MediumVC FragmentVC MAE-VC

Aishell-3

  1. F2F, 锁链叮叮铛铛的掉在石头地板上。
  2. F2M, 来一首那些花儿。
  3. M2F, 他正在开发监测用户在开车时是否在打盹儿的应用。
  4. M2M, 此次个人住房公积金存贷款利率相应调整。
Source Target ADAINVC AGAINVC MediumVC FragmentVC MAE-VC

Evaluation on mask ratio and FSC

VCTK

  1. F2F, Our dispute is with the company, not the travelling public.
  2. F2M, I feel we might now have the foundations to go forward.
  3. M2F, She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.
  4. M2M, The actual primary rainbow observed is said to be the effect of super-imposition of a number of bows.
Source Target Base_4c_16b_0r_w/o FSC Base_4c_16b_50r_w/o FSC Base_4c_16b_90r_w/o FSC Base_4c_16b_0r_FSC Base_4c_16b_50r_FSC Base_4c_16b_90r_FSC

Evaluation on bottleneck

VCTK

  1. F2F, Our dispute is with the company, not the travelling public.
  2. F2M, I feel we might now have the foundations to go forward.
  3. M2F, She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.
  4. M2M, The actual primary rainbow observed is said to be the effect of super-imposition of a number of bows.
Source Target Base_4c_2b_50r Base_4c_4b_50r Base_4c_8b_50r Base_4c_16b_50r Base_4c_36b_50r

Evaluation on cascaded number

VCTK

  1. F2F, Our dispute is with the company, not the travelling public.
  2. F2M, I feel we might now have the foundations to go forward.
  3. M2F, She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.
  4. M2M, The actual primary rainbow observed is said to be the effect of super-imposition of a number of bows.
Source Target Base_1c_2b_50r Base_2c_4b_50r Base_4c_8b_50r Base_6c_16b_50r Base_8c_36b_50r