We propose to use singular value decomposition (SVD) to reduce WaveNet parameters while maintaining its output voice quality. Specifically, we apply SVD on ...
Factorized WaveNet for voice conversion with limited data
www.sciencedirect.com › article › abs › pii
In this paper, we propose a factorized WaveNet for limited data tasks. Specifically, we apply singular value decomposition (SVD) on the dilated convolution ...
Jun 1, 2021 · In this paper, we propose a factorized WaveNet for limited data tasks. Specifically, we apply singular value decomposition (SVD) on the dilated ...
We propose a novel training scheme to optimize voice conversion network with a speaker identity loss function. The training scheme not only minimizes frame- ...
WAVENET FACTORIZATION WITH SINGULAR VALUE DECOMPOSITION FOR VOICE CONVERSION. Authors, Hongqiang Du, Northwestern Polytechnical University, China; Xiaohai ...
Jun 1, 2021 · WaveNet Factorization with Singular Value Decomposition for Voice Conversion ... singular value decomposition (SVD) to reduce WaveNet ...
WaveNet Factorization with Singular Value Decomposition for Voice Conversion ... This work proposes to use singular value decomposition (SVD) to reduce WaveNet ...
Li, “Wavenet factorization with singular value decomposition for voice conversion,” in 2019 IEEE Automatic. Speech Recognition and Understanding Workshop ...
Li, “Wavenet factorization with singular value decomposition for voice conversion,” in Proc. IEEE Autom. Speech Recognit. Understanding Workshop, 2019, pp ...
Apr 25, 2024 · Factorized WaveNet for voice conversion with limited data. ... WaveNet Factorization with Singular Value Decomposition for Voice Conversion.