# Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP

arXiv: https://arxiv.org/abs/2309.05423 · HTML: https://mlsanity.com/paper/2309.05423/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS](https://mlsanity.com/paper/2103.15060/) (2021)
- [PortaSpeech: Portable and High-Quality Generative Text-to-Speech](https://mlsanity.com/paper/2109.15166/) (2021)
- [Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions](https://mlsanity.com/paper/2301.08810/) (2023)
- [ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech](https://mlsanity.com/paper/2202.07816/) (2022)
- [DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021](https://mlsanity.com/paper/2110.12612/) (2021)
- [CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training](https://mlsanity.com/paper/2305.10763/) (2023)
- [Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech](https://mlsanity.com/paper/2203.17190/) (2022)
- [PPG-based singing voice conversion with adversarial representation learning](https://mlsanity.com/paper/2010.14804/) (2020)
- [BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model](https://mlsanity.com/paper/2207.01718/) (2022)
- [A Character-level Span-based Model for Mandarin Prosodic Structure Prediction](https://mlsanity.com/paper/2203.16922/) (2022)
- [Automatic Prosody Annotation with Pre-Trained Text-Speech Model](https://mlsanity.com/paper/2206.07956/) (2022)
- [On granularity of prosodic representations in expressive text-to-speech](https://mlsanity.com/paper/2301.11446/) (2023)
- [Low-Resource Mongolian Speech Synthesis Based on Automatic Prosody Annotation](https://mlsanity.com/paper/2211.09365/) (2022)

## Built on by (most cited first, 1 of 1)

- [The Impact of Prosodic Segmentation on Speech Synthesis of Spontaneous Speech](https://mlsanity.com/paper/2511.14779/) (2025)

## Abstract (arXiv)

In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual prosody annotation is labor-intensive and inconsistent. To address this issue, a two-stage automatic annotation pipeline is novelly proposed in this paper. In the first stage, we use contrastive pretraining of Speech-Silence and Word-Punctuation (SSWP) pairs to enhance prosodic information in latent representations. In the second stage, we build a multi-modal prosody annotator, comprising pretrained encoders, a text-speech fusing scheme, and a sequence classifier. Experiments on English prosodic boundaries demonstrate that our method achieves state-of-the-art (SOTA) performance with 0.72 and 0.93 f1 score for Prosodic Word and Prosodic Phrase boundary respectively, while bearing remarkable robustness to data scarcity.