# Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation

arXiv: https://arxiv.org/abs/2301.02262 · HTML: https://mlsanity.com/paper/2301.02262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 5 Jan 2023.

## Builds on (most cited first, 15 of 15)

- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention](https://mlsanity.com/paper/1710.08969/) (2017)
- [HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis](https://mlsanity.com/paper/2009.01776/) (2020)
- [XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System](https://mlsanity.com/paper/2006.06261/) (2020)
- [JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech](https://mlsanity.com/paper/2203.16852/) (2022)
- [Adversarially Trained End-to-end Korean Singing Voice Synthesis System](https://mlsanity.com/paper/1908.01919/) (2019)
- [ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders](https://mlsanity.com/paper/2004.11012/) (2020)
- [Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer](https://mlsanity.com/paper/1910.09989/) (2019)
- [Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System](https://mlsanity.com/paper/2108.02776/) (2021)
- [Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer](https://mlsanity.com/paper/2006.10317/) (2020)
- [PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components](https://mlsanity.com/paper/2102.07786/) (2021)
- [Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss](https://mlsanity.com/paper/2010.12024/) (2020)
- [Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN](https://mlsanity.com/paper/2209.10446/) (2022)

## Abstract (arXiv)

This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the timing of singing with temporal structures represented by scores, taking into account that there are differences between actual vocal timing and note start timing. In many SVS systems including our previous work, phoneme-level score features are converted into frame-level ones on the basis of phoneme boundaries obtained by external aligners to take into account vocal timing deviations. Therefore, the sound quality is affected by the aligner accuracy in this system. To alleviate this problem, we introduce an attention mechanism with frame-level features. In the proposed system, the attention mechanism absorbs alignment errors in phoneme boundaries. Additionally, we evaluate the system with pseudo-phoneme-boundaries defined by heuristic rules based on musical scores when there is no aligner. The experimental results show the effectiveness of the proposed system.