# Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech

arXiv: https://arxiv.org/abs/2406.05401 · HTML: https://mlsanity.com/paper/2406.05401/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2024.

## Built on by (most cited first, 5 of 5)

- [Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis](https://mlsanity.com/paper/2502.01084/) (2025)
- [Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis](https://mlsanity.com/paper/2507.00227/) (2025)
- [FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis](https://mlsanity.com/paper/2508.12001/) (2025)
- [Flamed-TTS: Flow Matching Attention-Free Models for Efficient Generating and Dynamic Pacing Zero-shot Text-to-Speech](https://mlsanity.com/paper/2510.02848/) (2025)
- [Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion](https://mlsanity.com/paper/2603.14032/) (2026)

## Abstract (arXiv)

Converting input symbols to output audio in TTS requires modelling the durations of speech sounds. Leading non-autoregressive (NAR) TTS models treat duration modelling as a regression problem. The same utterance is then spoken with identical timings every time, unlike when a human speaks. Probabilistic models of duration have been proposed, but there is mixed evidence of their benefits. However, prior studies generally only consider speech read aloud, and ignore spontaneous speech, despite the latter being both a more common and a more variable mode of speaking. We compare the effect of conventional deterministic duration modelling to durations sampled from a powerful probabilistic model based on conditional flow matching (OT-CFM), in three different NAR TTS approaches: regression-based, deep generative, and end-to-end. Across four different corpora, stochastic duration modelling improves probabilistic NAR TTS approaches, especially for spontaneous speech. Please see https://shivammehta25.github.io/prob_dur/ for audio and resources.