# Towards Multi-Scale Style Control for Expressive Speech Synthesis

arXiv: https://arxiv.org/abs/2104.03521 · HTML: https://mlsanity.com/paper/2104.03521/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [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)
- [Robust and fine-grained prosody control of end-to-end speech synthesis](https://mlsanity.com/paper/1811.02122/) (2018)
- [Fine-grained Emotion Strength Transfer, Control and Prediction for Emotional Speech Synthesis](https://mlsanity.com/paper/2011.08477/) (2020)
- [Fine-grained robust prosody transfer for single-speaker neural text-to-speech](https://mlsanity.com/paper/1907.02479/) (2019)
- [End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training](https://mlsanity.com/paper/1906.10859/) (2019)

## Built on by (most cited first, 18 of 18)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Emotion Intensity and its Control for Emotional Voice Conversion](https://mlsanity.com/paper/2201.03967/) (2022)
- [Speech Synthesis with Mixed Emotions](https://mlsanity.com/paper/2208.05890/) (2022)
- [GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech](https://mlsanity.com/paper/2205.07211/) (2022)
- [StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis](https://mlsanity.com/paper/2312.10741/) (2023)
- [StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing](https://mlsanity.com/paper/2402.12636/) (2024)
- [Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling](https://mlsanity.com/paper/2106.06233/) (2021)
- [STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent](https://mlsanity.com/paper/2203.14757/) (2022)
- [NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS](https://mlsanity.com/paper/2211.02448/) (2022)
- [Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings](https://mlsanity.com/paper/2407.14056/) (2024)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)
- [Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2305.16749/) (2023)
- [MAST: Multiscale Audio Spectrogram Transformers](https://mlsanity.com/paper/2211.01515/) (2022)
- [Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction](https://mlsanity.com/paper/2412.18748/) (2024)
- [A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis](https://mlsanity.com/paper/2309.11849/) (2023)
- [FluentEditor2: Text-based Speech Editing by Modeling Multi-Scale Acoustic and Prosody Consistency](https://mlsanity.com/paper/2410.03719/) (2024)
- [Towards Cross-speaker Reading Style Transfer on Audiobook Dataset](https://mlsanity.com/paper/2208.05359/) (2022)
- [CASEIN: Cascading Explicit and Implicit Control for Fine-grained Emotion Intensity Regulation](https://mlsanity.com/paper/2307.00020/) (2023)

## Abstract (arXiv)

This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis. The proposed method employs a multi-scale reference encoder to extract both the global-scale utterance-level and the local-scale quasi-phoneme-level style features of the target speech, which are then fed into the speech synthesis model as an extension to the input phoneme sequence. During training time, the multi-scale style model could be jointly trained with the speech synthesis model in an end-to-end fashion. By applying the proposed method to style transfer task, experimental results indicate that the controllability of the multi-scale speech style model and the expressiveness of the synthesized speech are greatly improved. Moreover, by assigning different reference speeches to extraction of style on each scale, the flexibility of the proposed method is further revealed.