Global Prosody Style Transfer Without Text Transcriptions

Authors: Kaizhi Qian, Yang Zhang, Shiyu Chang, Jinjun Xiong, Chuang Gan, David Cox, Mark Hasegawa-Johnson

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on different style transfer tasks show that AUTOPST can effectively convert prosody that correctly reflects the styles of the target domains.
Researcher Affiliation Collaboration 1MIT-IBM Watson AI Lab, USA 2IBM Thomas J. Watson AI Lab, USA 3University of Illinois at Urbana-Champaign, USA.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No We encourage readers to listen to our online demo audios1. 1https://auspicious3000.github.io/AutoPST-Demo
Open Datasets Yes Our dataset is VCTK (Veaux et al., 2016), which consists of 44 hours of speech from 109 speakers.
Dataset Splits No We use 24 speakers for training and follow the same train/test partition as in (Qian et al., 2020b).
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper mentions that the decoder is a Transformer and a WaveNet vocoder is used, but does not specify software library names with version numbers for reproducibility (e.g., PyTorch, TensorFlow, CUDA).
Experiment Setup Yes More hyperparameters setting details can be found in Appendix C.