AAS-VC: On the Generalization Ability of Automatic Alignment Search based Non-autoregressive Sequence-to-sequence Voice Conversion
Abstract
Non-autoregressive (non-AR) sequence-to-seqeunce (seq2seq) models for voice conversion (VC) is attractive in its ability to effectively model the temporal structure while enjoying boosted intelligibility and fast inference thanks to non-AR modeling. However, the dependency of current non-AR seq2seq VC models on ground truth durations extracted from an external AR model greatly limits its generalization ability to smaller training datasets. In this paper, we first demonstrate the above-mentioned problem by varying the training data size. Then, we present AAS-VC, a non-AR seq2seq VC model based on automatic alignment search (AAS), which removes the dependency on external durations and serves as a proper inductive bias to provide the required generalization ability for small datasets. Experimental results show that AAS-VC can generalize better to a training dataset of only 5 minutes. We also conducted ablation studies to justify several model design choices. The audio samples and implementation are available online.
Keywords
Cite
@article{arxiv.2309.07598,
title = {AAS-VC: On the Generalization Ability of Automatic Alignment Search based Non-autoregressive Sequence-to-sequence Voice Conversion},
author = {Wen-Chin Huang and Kazuhiro Kobayashi and Tomoki Toda},
journal= {arXiv preprint arXiv:2309.07598},
year = {2023}
}
Comments
Submitted to ICASSP 2024. Demo: https://unilight.github.io/Publication-Demos/publications/aas-vc/index.html. Code: https://github.com/unilight/seq2seq-vc