# Word-Level Style Control for Expressive, Non-attentive Speech Synthesis

arXiv: https://arxiv.org/abs/2111.10173 · HTML: https://mlsanity.com/paper/2111.10173/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 19 Nov 2021.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [LPCNet: Improving Neural Speech Synthesis Through Linear Prediction](https://mlsanity.com/paper/1810.11846/) (2018)
- [Hierarchical Generative Modeling for Controllable Speech Synthesis](https://mlsanity.com/paper/1810.07217/) (2018)
- [Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling](https://mlsanity.com/paper/2010.04301/) (2020)
- [Learning latent representations for style control and transfer in end-to-end speech synthesis](https://mlsanity.com/paper/1812.04342/) (2018)
- [Robust and fine-grained prosody control of end-to-end speech synthesis](https://mlsanity.com/paper/1811.02122/) (2018)
- [Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis](https://mlsanity.com/paper/2002.03785/) (2020)
- [DurIAN: Duration Informed Attention Network For Multimodal Synthesis](https://mlsanity.com/paper/1909.01700/) (2019)
- [Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior](https://mlsanity.com/paper/2002.03788/) (2020)
- [Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis](https://mlsanity.com/paper/1808.01410/) (2018)
- [Fine-grained robust prosody transfer for single-speaker neural text-to-speech](https://mlsanity.com/paper/1907.02479/) (2019)
- [CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network](https://mlsanity.com/paper/1905.07195/) (2019)
- [CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech](https://mlsanity.com/paper/2004.14617/) (2020)
- [High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency](https://mlsanity.com/paper/2111.09052/) (2021)
- [Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis](https://mlsanity.com/paper/2009.08474/) (2020)
- [Uncovering Latent Style Factors for Expressive Speech Synthesis](https://mlsanity.com/paper/1711.00520/) (2017)

## Built on by (most cited first, 5 of 5)

- [ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech](https://mlsanity.com/paper/2202.07816/) (2022)
- [SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis](https://mlsanity.com/paper/2204.03040/) (2022)
- [Controllable speech synthesis by learning discrete phoneme-level prosodic representations](https://mlsanity.com/paper/2211.16307/) (2022)
- [Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis](https://mlsanity.com/paper/2211.00523/) (2022)
- [Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis](https://mlsanity.com/paper/2211.01327/) (2022)

## Abstract (arXiv)

This paper presents an expressive speech synthesis architecture for modeling and controlling the speaking style at a word level. It attempts to learn word-level stylistic and prosodic representations of the speech data, with the aid of two encoders. The first one models style by finding a combination of style tokens for each word given the acoustic features, and the second outputs a word-level sequence conditioned only on the phonetic information in order to disentangle it from the style information. The two encoder outputs are aligned and concatenated with the phoneme encoder outputs and then decoded with a Non-Attentive Tacotron model. An extra prior encoder is used to predict the style tokens autoregressively, in order for the model to be able to run without a reference utterance. We find that the resulting model gives both word-level and global control over the style, as well as prosody transfer capabilities.