ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

2026-06-20

AI Summary

This work addresses the challenge that existing controllable text-to-speech (TTS) systems struggle to automatically infer appropriate prosodic styles in complex conversational scenarios, often requiring explicit user-provided style cues. To overcome this limitation, we propose the first context-aware, end-to-end speech synthesis framework that integrates Chain-of-Thought (CoT) reasoning into TTS, enabling the model to generate contextually appropriate speech directly from textual or acoustic context while simultaneously producing interpretable reasoning traces. We construct a high-quality bilingual dataset for training and evaluation, employ a three-stage fine-tuning strategy based on Qwen3-0.6B, and establish a dual-track evaluation framework combining multimodal large models and human assessment. Our approach significantly enhances vocal expressiveness and contextual consistency, demonstrating strong applicability in high-fidelity domains such as film dubbing and audiobook narration. The code and fine-tuning recipes are publicly released for reproducibility.

Abstract

Recent advances in text-to-speech (TTS) have greatly improved speech naturalness, speaker similarity, and controllability. However, most existing controllable TTS systems still rely on explicit user-provided style prompts, making it difficult to automatically determine how a sentence should be spoken in long and complex conversational scenarios. This proposal introduces the ISCSLP 2026 CoT-TTS Challenge, which aims to evaluate whether a system can infer the intended speaking manner from contextual information and generate speech consistent with both the reasoning output and the surrounding scene. The challenge contains two tracks: text-context-aware CoT-TTS and audio-context-aware CoT-TTS. We construct a large-scale bilingual training set from speech-rich media and provide carefully filtered evaluation data for leaderboard comparison. Each system is required to output both a chain-of-thought reasoning analysis and the generated speech waveform. The official evaluation combines objective metrics, multimodal LLM-based evaluation, and human subjective assessment. To facilitate reproducibility, we provide inference code together with a fine-tuning recipe for a 0.6B Qwen3-based model trained via a three-stage strategy. This challenge is expected to support research on context understanding, chain-of-thought reasoning, and expressive speech generation for applications such as film dubbing, audiobook production, virtual characters, and spoken dialogue agents. Further information about the associated challenge is available at:https://iscslp2026-cot-tts.github.io/challenge-website/

Problem

• Text-to-Speech
• Context-Aware
• Chain-of-Thought
• Expressive Speech
• Conversational TTS

Innovation

• Chain-of-Thought Reasoning
• Context-Aware TTS
• Expressive Speech Synthesis
• Multimodal Evaluation
• Controllable TTS