Paper ID | SPE-12.1 | ||
Paper Title | TOWARDS LOW-RESOURCE STARGAN VOICE CONVERSION USING WEIGHT ADAPTIVE INSTANCE NORMALIZATION | ||
Authors | Mingjie Chen, Yanpei Shi, Thomas Hain, University of Sheffield, United Kingdom | ||
Session | SPE-12: Voice Conversion 2: Low-Resource & Cross-Lingual Conversion | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-SYNT] Speech Synthesis and Generation | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Many-to-many voice conversion with non-parallel training data has seen significant progress in recent years. It is challenging because of lacking of ground truth parallel data. StarGAN-based models have gained attentions because of their efficiency and effectiveness. However, most of the StarGAN-based works only focused on small number of speakers and large amount of training data. In this work, we aim at improving the data efficiency of the model and achieving a many-to-many non-parallel StarGAN-based voice conversion for a relatively large number of speakers with limited training samples. In order to improve data efficiency, the proposed model uses a speaker encoder for extracting speaker embeddings and weight adaptive instance normalization (W-AdaIN) layers. Experiments are conducted with 109 speakers under two low-resource situations, where the number of training samples is 20 and 5 per speaker. An objective evaluation shows the proposed model outperforms baseline methods significantly. Furthermore, a subjective evaluation shows that, for both naturalness and similarity, the proposed model outperforms baseline method. |