# Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech

arXiv: https://arxiv.org/abs/2609.36974 · HTML: https://mlsanity.com/paper/2609.36974/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 22 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Theoretical Limitations of Self-Attention in Neural Sequence Models](https://mlsanity.com/paper/1906.06755/) (2019)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [What Formal Languages Can Transformers Express? A Survey](https://mlsanity.com/paper/2311.00208/) (2023)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Transformers need glasses! Information over-squashing in language tasks](https://mlsanity.com/paper/2406.04267/) (2024)
- [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://mlsanity.com/paper/2502.04128/) (2025)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [(How) Do Language Models Track State?](https://mlsanity.com/paper/2503.02854/) (2025)
- [Counting Ability of Large Language Models and Impact of Tokenization](https://mlsanity.com/paper/2410.19730/) (2024)
- [RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis](https://mlsanity.com/paper/2404.03204/) (2024)
- [The Counting Power of Transformers](https://mlsanity.com/paper/2505.11199/) (2025)
- [Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs](https://mlsanity.com/paper/2605.09239/) (2026)
- [From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales](https://mlsanity.com/paper/2604.08591/) (2026)

## Abstract (arXiv)

Text-to-speech models loop, truncate and lose count on text that repeats a phrase many times. We show that repetition itself is what breaks them, not the length that comes with it. Every repeated sentence in our test set is paired with a control of matched sentence and word count in which no word ever repeats back-to-back. Six models from three architectures render the controls almost perfectly and fail the repeated twins: 94.3% against 18.2% exactly right at k >= 6. The gap survives greedy decoding, repetition-penalty sweeps, four independent speech recognisers and 420 analysis specifications without once reversing sign; a held-out fourth architecture lands within a point of its predicted gap, and one of two non-autoregressive baselines shows the same failure. Varying the period of the text shows the failure grows smoothly with periodicity, half of it surviving when no word is adjacent to itself.