Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph
Zero-shot voice conversion samples
Note:
1. To distinguish all the details of different conversion results, please wear headphones when listening to the following samples.
2. 'target' means the voice conversion system extracts style information directly from the utterance in this column.
3. 'authentic target' is shown for the convenience of comparison. It shows the real recording of the target speaker speaking the same sentence as source utterance.
However, the voice conversion system does not use this authentic target utterance when converting the voice. Instead, other utterances spoken by the same target speaker are fed into the voice conversion system for style extraction.
Librispeech samples
Source
Target
Converted
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
System comparison (style extracted from 5 target utterances)
Source
Authentic Target
AutoVC
AdaIN-VC
FragmentVC
S2VC
Retriever(ours)
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Conversion results of using different number of style token
Source
Authentic Target
1 style token
5 style tokens
10 style tokens
60 style tokens
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Ablation
Source
Authentic Target
Too narrow bottleneck
Too wide bottleneck
AdaIN decoder
Retriever
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Conversion result of using different number of target utterances during inference
Source
Authentic Target
1 target utterance
3 target utterance
5 target utterance
10 target utterance
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.
Your browser does not support the audio element.