# Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation

arXiv: https://arxiv.org/abs/2603.21078 · HTML: https://mlsanity.com/paper/2603.21078/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 22 Mar 2026.

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

- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [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)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training](https://mlsanity.com/paper/2305.10763/) (2023)
- [Forensic deepfake audio detection using segmental speech features](https://mlsanity.com/paper/2505.13847/) (2025)

## Built on by (most cited first, 3 of 3)

- [Acoustic and perceptual differences between standard and accented speech and their voice clones](https://mlsanity.com/paper/2604.01562/) (2026)
- [The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints](https://mlsanity.com/paper/2608.07980/) (2026)
- [A survey of AI-generated voices and their detection](https://mlsanity.com/paper/2608.15411/) (2026)

## Abstract (arXiv)

This study proposes a segmental-level prosodic probing framework to evaluate neural TTS models' ability to reproduce consonant-induced f0 perturbation, a fine-grained segmental-prosodic effect that reflects local articulatory mechanisms. We compare synthetic and natural speech realizations for thousands of words, stratified by lexical frequency, using Tacotron 2 and FastSpeech 2 trained on the same speech corpus (LJ Speech). These controlled analyses are then complemented by a large-scale evaluation spanning multiple advanced TTS systems. Results show accurate reproduction for high-frequency words but poor generalization to low-frequency items, suggesting that the examined TTS architectures rely more on lexical-level memorization than on abstract segmental-prosodic encoding. This finding highlights a limitation in such TTS systems' ability to generalize prosodic detail beyond seen data. The proposed probe offers a linguistically informed diagnostic framework that may inform future TTS evaluation methods, and has implications for interpretability and authenticity assessment in synthetic speech.