# Long-Context Speech Synthesis with Context-Aware Memory

arXiv: https://arxiv.org/abs/2508.14713 · HTML: https://mlsanity.com/paper/2508.14713/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2025.

## Built on by (most cited first, 1 of 1)

- [MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data](https://mlsanity.com/paper/2606.18485/) (2026)

## Abstract (arXiv)

In long-text speech synthesis, current approaches typically convert text to speech at the sentence-level and concatenate the results to form pseudo-paragraph-level speech. These methods overlook the contextual coherence of paragraphs, leading to reduced naturalness and inconsistencies in style and timbre across the long-form speech. To address these issues, we propose a Context-Aware Memory (CAM)-based long-context Text-to-Speech (TTS) model. The CAM block integrates and retrieves both long-term memory and local context details, enabling dynamic memory updates and transfers within long paragraphs to guide sentence-level speech synthesis. Furthermore, the prefix mask enhances the in-context learning ability by enabling bidirectional attention on prefix tokens while maintaining unidirectional generation. Experimental results demonstrate that the proposed method outperforms baseline and state-of-the-art long-context methods in terms of prosody expressiveness, coherence and context inference cost across paragraph-level speech.