# Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model

arXiv: https://arxiv.org/abs/2305.16749 · HTML: https://mlsanity.com/paper/2305.16749/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 21 of its 23 references that are in the map.
- First posted on arXiv 26 May 2023.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [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)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [Diff-TTS: A Denoising Diffusion Model for Text-to-Speech](https://mlsanity.com/paper/2104.01409/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis](https://mlsanity.com/paper/2203.13508/) (2022)
- [Robust and fine-grained prosody control of end-to-end speech synthesis](https://mlsanity.com/paper/1811.02122/) (2018)
- [DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs](https://mlsanity.com/paper/2201.11972/) (2022)
- [Revisiting Over-Smoothness in Text to Speech](https://mlsanity.com/paper/2202.13066/) (2022)
- [ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech](https://mlsanity.com/paper/2202.07816/) (2022)
- [Towards Multi-Scale Style Control for Expressive Speech Synthesis](https://mlsanity.com/paper/2104.03521/) (2021)
- [CAMP: a Two-Stage Approach to Modelling Prosody in Context](https://mlsanity.com/paper/2011.01175/) (2020)
- [Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis](https://mlsanity.com/paper/2203.12201/) (2022)

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

- [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://mlsanity.com/paper/2502.04128/) (2025)
- [DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training](https://mlsanity.com/paper/2307.16549/) (2023)
- [Multi-modal Adversarial Training for Zero-Shot Voice Cloning](https://mlsanity.com/paper/2408.15916/) (2024)
- [Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters](https://mlsanity.com/paper/2610.05575/) (2026)

## Abstract (arXiv)

Expressive human speech generally abounds with rich and flexible speech prosody variations. The speech prosody predictors in existing expressive speech synthesis methods mostly produce deterministic predictions, which are learned by directly minimizing the norm of prosody prediction error. Its unimodal nature leads to a mismatch with ground truth distribution and harms the model's ability in making diverse predictions. Thus, we propose a novel prosody predictor based on the denoising diffusion probabilistic model to take advantage of its high-quality generative modeling and training stability. Experiment results confirm that the proposed prosody predictor outperforms the deterministic baseline on both the expressiveness and diversity of prediction results with even fewer network parameters.