ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement

Gyeong-Hoon Lee, Tae-Woo Kim, Hanbin Bae, Min-Ji Lee, Young-Ik Kim, Hoon-Young Cho

Recently, end-to-end Korean singing voice systems have been designed to generate realistic singing voices. However, these systems still suffer from a lack of robustness in terms of pronunciation accuracy. In this paper, we propose N-Singer, a non-autoregressive Korean singing voice system, to synthesize accurate and pronounced Korean singing voices in parallel. N-Singer consists of a Transformer-based mel-generator, a convolutional network-based postnet, and voicing-aware discriminators. It can contribute in the following ways. First, for accurate pronunciation, N-Singer separately models linguistic and pitch information without other acoustic features. Second, to achieve improved mel-spectrograms, N-Singer uses a combination of Transformer-based modules and convolutional network-based modules. Third, in adversarial training, voicing-aware conditional discriminators are used to capture the harmonic features of voiced segments and noise components of unvoiced segments. The experimental results prove that N-Singer can synthesize a natural singing voice in parallel with a more accurate pronunciation than the baseline model.


doi: 10.21437/Interspeech.2021-239

Cite as: Lee, G.-H., Kim, T.-W., Bae, H., Lee, M.-J., Kim, Y.-I., Cho, H.-Y. (2021) N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement. Proc. Interspeech 2021, 1589-1593, doi: 10.21437/Interspeech.2021-239

@inproceedings{lee21b_interspeech,
  author={Gyeong-Hoon Lee and Tae-Woo Kim and Hanbin Bae and Min-Ji Lee and Young-Ik Kim and Hoon-Young Cho},
  title={{N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1589--1593},
  doi={10.21437/Interspeech.2021-239}
}