# Improving French Synthetic Speech Quality via SSML Prosody Control

arXiv: https://arxiv.org/abs/2508.17494 · HTML: https://mlsanity.com/paper/2508.17494/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio](https://mlsanity.com/paper/2501.11378/) (2025)
- [Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis](https://mlsanity.com/paper/2104.12395/) (2021)
- [Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech](https://mlsanity.com/paper/2011.02252/) (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)
- [Emphasis control for parallel neural TTS](https://mlsanity.com/paper/2110.03012/) (2021)
- [Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems](https://mlsanity.com/paper/2206.15067/) (2022)
- [Supervised and Unsupervised Approaches for Controlling Narrow Lexical Focus in Sequence-to-Sequence Speech Synthesis](https://mlsanity.com/paper/2101.09940/) (2021)
- [DrawSpeech: Expressive Speech Synthesis Using Prosodic Sketches as Control Conditions](https://mlsanity.com/paper/2501.04256/) (2025)
- [PSST! Prosodic Speech Segmentation with Transformers](https://mlsanity.com/paper/2302.01984/) (2023)
- [EE-TTS: Emphatic Expressive TTS with Linguistic Information](https://mlsanity.com/paper/2305.12107/) (2023)
- [An investigation of phrase break prediction in an End-to-End TTS system](https://mlsanity.com/paper/2304.04157/) (2023)
- [Going Retro: Astonishingly Simple Yet Effective Rule-based Prosody Modelling for Speech Synthesis Simulating Emotion Dimensions](https://mlsanity.com/paper/2307.02132/) (2023)

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

- [Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages](https://mlsanity.com/paper/2608.27848/) (2026)

## Abstract (arXiv)

Despite recent advances, synthetic voices often lack expressiveness due to limited prosody control in commercial text-to-speech (TTS) systems. We introduce the first end-to-end pipeline that inserts Speech Synthesis Markup Language (SSML) tags into French text to control pitch, speaking rate, volume, and pause duration. We employ a cascaded architecture with two QLoRA-fine-tuned Qwen 2.5-7B models: one predicts phrase-break positions and the other performs regression on prosodic targets, generating commercial TTS-compatible SSML markup. Evaluated on a 14-hour French podcast corpus, our method achieves 99.2% F1 for break placement and reduces mean absolute error on pitch, rate, and volume by 25-40% compared with prompting-only large language models (LLMs) and a BiLSTM baseline. In perceptual evaluation involving 18 participants across over 9 hours of synthesized audio, SSML-enhanced speech generated by our pipeline significantly improves naturalness, with the mean opinion score increasing from 3.20 to 3.87 (p < 0.005). Additionally, 15 of 18 listeners preferred our enhanced synthesis. These results demonstrate substantial progress in bridging the expressiveness gap between synthetic and natural French speech. Our code is publicly available at https://github.com/hi-paris/Prosody-Control-French-TTS.