TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis

TL;DR

TED-TTS introduces a training-free, controllable TTS framework that enables fine-grained intra-utterance emotion and duration control using a novel segment-aware conditioning strategy, without requiring additional training or manual prompts.

Contribution

It proposes a novel training-free approach for intra-utterance emotion and duration control in TTS, utilizing segment-aware strategies and automatic prompt construction from a large annotated dataset.

Findings

Achieves state-of-the-art intra-utterance consistency in multi-emotion and duration control.

Maintains baseline speech quality while enabling fine-grained control.

Demonstrates effectiveness through extensive experiments.

Abstract

While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public datasets or complex multi-stage training. In this paper, we propose TED-TTS, a training-free controllable framework for pretrained zero-shot TTS to enable intra-utterance emotion and duration expression. Specifically, we propose a segment-aware emotion conditioning strategy that combines causal masking with monotonic stream alignment filtering to isolate emotion conditioning and schedule mask transitions, enabling smooth intra-utterance emotion shifts while preserving global semantic coherence. Based on this, we further propose a segment-aware duration steering strategy to combine local duration embedding steering with global EOS logit modulation, allowing local duration adjustment while ensuring globally consistent termination. To eliminate the need for segment-level manual prompt engineering, we construct a 30,000-sample multi-emotion and duration-annotated text dataset to enable LLM-based automatic prompt construction. Extensive experiments demonstrate that our training-free method not only achieves state-of-the-art intra-utterance consistency in multi-emotion and duration control, but also maintains baseline-level speech quality of the underlying TTS model. Code and audio samples are available.