# Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis

arXiv: https://arxiv.org/abs/2202.07907 · HTML: https://mlsanity.com/paper/2202.07907/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [LPCNet: Improving Neural Speech Synthesis Through Linear Prediction](https://mlsanity.com/paper/1810.11846/) (2018)
- [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)
- [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)
- [Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis](https://mlsanity.com/paper/1807.06736/) (2018)
- [Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer](https://mlsanity.com/paper/1910.09989/) (2019)
- [A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis](https://mlsanity.com/paper/1906.09573/) (2019)
- [Singing Synthesis: with a little help from my attention](https://mlsanity.com/paper/1912.05881/) (2019)
- [Singing voice synthesis based on convolutional neural networks](https://mlsanity.com/paper/1904.06868/) (2019)

## Built on by (most cited first, 4 of 4)

- [CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance](https://mlsanity.com/paper/2509.19883/) (2025)
- [Karaoker: Alignment-free singing voice synthesis with speech training data](https://mlsanity.com/paper/2204.04127/) (2022)
- [Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism](https://mlsanity.com/paper/2212.13703/) (2022)
- [LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learning](https://mlsanity.com/paper/2507.04966/) (2025)

## Abstract (arXiv)

End-to-end singing voice synthesis (SVS) is attractive due to the avoidance of pre-aligned data. However, the auto learned alignment of singing voice with lyrics is difficult to match the duration information in musical score, which will lead to the model instability or even failure to synthesize voice. To learn accurate alignment information automatically, this paper proposes an end-to-end SVS framework, named Singing-Tacotron. The main difference between the proposed framework and Tacotron is that the speech can be controlled significantly by the musical score's duration information. Firstly, we propose a global duration control attention mechanism for the SVS model. The attention mechanism can control each phoneme's duration. Secondly, a duration encoder is proposed to learn a set of global transition tokens from the musical score. These transition tokens can help the attention mechanism decide whether moving to the next phoneme or staying at each decoding step. Thirdly, to further improve the model's stability, a dynamic filter is designed to help the model overcome noise interference and pay more attention to local context information. Subjective and objective evaluation verify the effectiveness of the method. Furthermore, the role of global transition tokens and the effect of duration control are explored. Examples of experiments can be found at https://hairuo55.github.io/SingingTacotron.