Conditional End-to-End Audio Transforms

Michelle Guo
Michelle Guo
Prateek Verma
Prateek Verma

Interspeech, pp. 2295-2299, 2018.

Cited by: 17|Bibtex|Views25|DOI:https://doi.org/10.21437/interspeech.2018-38
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target voices. For the case of music, we can specify musical instruments and achieve the same result. Archit...More

Code:

Data:

Your rating :
0

 

Tags
Comments