# Controllable Emphasis with zero data for text-to-speech

arXiv: https://arxiv.org/abs/2307.07062 · HTML: https://mlsanity.com/paper/2307.07062/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 13 Jul 2023.

## Builds on (most cited first, 9 of 9)

- [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)
- [Deep Voice: Real-time Neural Text-to-Speech](https://mlsanity.com/paper/1702.07825/) (2017)
- [Universal Neural Vocoding with Parallel WaveNet](https://mlsanity.com/paper/2102.01106/) (2021)
- [CAMP: a Two-Stage Approach to Modelling Prosody in Context](https://mlsanity.com/paper/2011.01175/) (2020)
- [CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer](https://mlsanity.com/paper/2206.13443/) (2022)
- [Expressive, Variable, and Controllable Duration Modelling in TTS](https://mlsanity.com/paper/2206.14165/) (2022)
- [Distribution augmentation for low-resource expressive text-to-speech](https://mlsanity.com/paper/2202.06409/) (2022)
- [Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody](https://mlsanity.com/paper/2206.14643/) (2022)

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

- [BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data](https://mlsanity.com/paper/2402.08093/) (2024)
- [You Sound a Little Tense: L2 Tailored Clear TTS Using Durational Vowel Properties](https://mlsanity.com/paper/2506.23367/) (2025)
- [Emphasis Sensitivity in Speech Representations](https://mlsanity.com/paper/2508.11566/) (2025)
- [Do Speech Emphasis Models Generalize across Languages and Emotions?](https://mlsanity.com/paper/2606.27717/) (2026)

## Abstract (arXiv)

We present a scalable method to produce high quality emphasis for text-to-speech (TTS) that does not require recordings or annotations. Many TTS models include a phoneme duration model. A simple but effective method to achieve emphasized speech consists in increasing the predicted duration of the emphasised word. We show that this is significantly better than spectrogram modification techniques improving naturalness by 7.3% and correct testers' identification of the emphasized word in a sentence by 40% on a reference female en-US voice. We show that this technique significantly closes the gap to methods that require explicit recordings. The method proved to be scalable and preferred in all four languages tested (English, Spanish, Italian, German), for different voices and multiple speaking styles.