The Problem of Robotic Voice When Changing Speech Speed - From Phase Vocoder to WSOLA
DEV Community
The Problem of Robotic Voice When Changing Speech Speed - From Phase Vocoder to WSOLA
When trying to change speech speed while preserving pitch, using librosa's phase vocoder results in a metallic echo. The cause is phase smearing, and this is a record of resolving the issue by implementing WSOLA from scratch using numpy.
0 comments
No comments yet.