# CAMP: a Two-Stage Approach to Modelling Prosody in Context

arXiv: https://arxiv.org/abs/2011.01175 · HTML: https://mlsanity.com/paper/2011.01175/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model](https://mlsanity.com/paper/2207.01718/) (2022)
- [ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS](https://mlsanity.com/paper/2209.06484/) (2022)
- [A learned conditional prior for the VAE acoustic space of a TTS system](https://mlsanity.com/paper/2106.10229/) (2021)
- [Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2305.16749/) (2023)
- [Controllable Emphasis with zero data for text-to-speech](https://mlsanity.com/paper/2307.07062/) (2023)
- [Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech](https://mlsanity.com/paper/2110.12539/) (2021)
- [Controllable speech synthesis by learning discrete phoneme-level prosodic representations](https://mlsanity.com/paper/2211.16307/) (2022)
- [A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis](https://mlsanity.com/paper/2208.02189/) (2022)
- [Controllable Prosody Generation With Partial Inputs](https://mlsanity.com/paper/2303.09446/) (2023)
- [Multi-Scale Spectrogram Modelling for Neural Text-to-Speech](https://mlsanity.com/paper/2106.15649/) (2021)
- [Towards Cross-speaker Reading Style Transfer on Audiobook Dataset](https://mlsanity.com/paper/2208.05359/) (2022)
- [VisualSpeech: Enhancing Prosody Modeling in TTS Using Video](https://mlsanity.com/paper/2501.19258/) (2025)

## Abstract (arXiv)

Prosody is an integral part of communication, but remains an open problem in state-of-the-art speech synthesis. There are two major issues faced when modelling prosody: (1) prosody varies at a slower rate compared with other content in the acoustic signal (e.g. segmental information and background noise); (2) determining appropriate prosody without sufficient context is an ill-posed problem. In this paper, we propose solutions to both these issues. To mitigate the challenge of modelling a slow-varying signal, we learn to disentangle prosodic information using a word level representation. To alleviate the ill-posed nature of prosody modelling, we use syntactic and semantic information derived from text to learn a context-dependent prior over our prosodic space. Our Context-Aware Model of Prosody (CAMP) outperforms the state-of-the-art technique, closing the gap with natural speech by 26%. We also find that replacing attention with a jointly-trained duration model improves prosody significantly.