eess.ASNov 15, 2026

ProTTS: End-to-End Prominence-aware Natural and Controllable Text-to-Speech via Automatic Word Stress Discovery

Authors: Sai Harshitha Aluru, Chiranjeevi Yarra

Organizations: Speech Processing Lab, LTRC IIIT Hyderabad Hyderabad, India

Abstract

Natural speech conveys meaning not only through words, but also through the prominence on a few words. Yet most text-to-speech (TTS) systems remain prominence-unaware, existing prominence-aware TTS require external stress annotations, while unsupervised stress detectors operate in isolation, disconnected from synthesis. This creates a fundamental gap no existing system can automatically discover where stress should be placed, realize it as natural-sounding prosody, and offer user control over emphasis placement, all within a single model. To circumvent this, we propose ProTTS, a unified framework where stress detection emerges from the TTS model itself and, in turn, guides it to synthesize more natural and controllable speech. We incorporate a clustering head into the variance adaptor of FastSpeech_2 that discovers word stress directly from aggregated prosodic features. The discovered stress then drives emphasis variance predictors that modify pitch, energy, and duration for stressed words. The framework is trained end-to-end: TTS reconstruction and clustering losses jointly shape a stress-discriminative feature space without requiring stress labels at any stage. At inference, the same architecture also supports user-controllable emphasis by accepting a custom stress mask. We evaluate ProTTS on ISLE (non-native), LibriTTS, VCTK (native training), and three evaluation benchmarks (Tatoeba, TinyStress-15k, EmphAssess). Listeners prefer ProTTS over the baseline with a MOS of 3.96 vs. 3.12 and 83.5% preference rate. For stress detection, ProTTS achieves 0.839/0.861 F1 on ISLE (German/Italian L2), outperforming unsupervised (0.70) and supervised (0.82) baselines, and 0.933 F1 in zero-shot transfer to Tatoeba.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EmphTTS: an emphasis-control TTS with reinforcement learning

    Sep 23, 2026Zirui Li, Rech Silas, Lauri Juvela +2TTS SynthesisControllable Speech Generation

  2. Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark

    Apr 12, 2026Arnon Turetzky, Avihu Dekel, Hagai Aronowitz +2TTS SynthesisTTS Evaluation

  3. StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis

    Jul 22, 2026Kaicheng Luo, Xuefei Gong, Yutao Sun +6TTS SynthesisSpeech Prosody