CAST-TTS: A Simple Cross-Attention Framework for Unified Timbre Control in TTS

TL;DR

CAST-TTS introduces a unified cross-attention framework that effectively combines speech and text prompts for timbre control in TTS, simplifying architecture while maintaining high-quality synthesis.

Contribution

It proposes a simple, multi-stage training framework with a shared embedding space and a single cross-attention mechanism for unified timbre control in TTS.

Findings

Achieves performance comparable to specialized models

Effectively aligns speech and text representations

Validates the importance of cross-attention for quality

Abstract

Current Text-to-Speech (TTS) systems typically use separate models for speech-prompted and text-prompted timbre control. While unifying both control signals into a single model is desirable, the challenge of cross-modal alignment often results in overly complex architectures and training objective. To address this challenge, we propose CAST-TTS, a simple yet effective framework for unified timbre control. Features are extracted from speech prompts and text prompts using pre-trained encoders. The multi-stage training strategy efficiently aligns the speech and projected text representations within a shared embedding space. A single cross-attention mechanism then allows the model to use either of these representations to control the timbre. Extensive experiments validate that the unified cross-attention mechanism is critical for achieving high-quality synthesis. CAST-TTS achieves performance comparable to specialized single-input models while operating within a unified architecture. The demo page can be accessed at https://HiRookie9.github.io/CAST-TTS-Page.