Skip to content

Why is the speaker embedding g used to condition the Posterior Encoder and the Decoder? #88

@st-vincent1

Description

@st-vincent1

I am confused why the speaker embedding g is used to condition multiple model components (Posterior Encoder, Decoder, Flow) as opposed to just Flow.

From the model diagram in Fig. 1 (a) (Training procedure), the speaker embedding g is used to condition the normalising Flow. This makes sense: at inference time, this information in the reversed Flow to reverse the z' distribution into a speaker-informed z which was modelled after the real data x_lin with the Posterior Encoder.

To me this seems like enough supervision, and I am confused why g is used in other places too:

  • in Posterior Encoder which uses x_lin as input, g is also supplied - but it shouldn't be needed as x_lin already contains the speaker information! (And g is not mentioned in section 2.2.2. of the paper when this encoder is discussed)
  • in Decoder, similarly, z is already informed with the speaker embedding, so why do we need to explicitly supply it here?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions