# DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching

arXiv: https://arxiv.org/abs/2510.08373 · HTML: https://mlsanity.com/paper/2510.08373/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2025.

## Built on by (most cited first, 3 of 3)

- [Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modeling](https://mlsanity.com/paper/2602.08233/) (2026)
- [Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors](https://mlsanity.com/paper/2606.19325/) (2026)
- [KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction](https://mlsanity.com/paper/2609.07200/) (2026)

## Abstract (arXiv)

Recent advances in text-to-speech (TTS) synthesis, particularly those leveraging large language models (LLMs), have significantly improved expressiveness and naturalness. However, generating human-like, interactive dialogue speech remains challenging. Current systems face limitations due to the scarcity of dual-track data and difficulties in achieving naturalness, contextual coherence, and interactional dynamics, such as turn-taking, overlapping speech, and speaker consistency, in multi-turn conversations. To address these challenges, we propose DialoSpeech, a dual-track architecture combining a large language model with Chunked Flow Matching for expressive, human-like dialogue speech synthesis. DialoSpeech generates natural multi-turn conversations with coherent speaker turns and natural overlaps, supporting both Chinese and English and cross-lingual speech synthesis. We introduce a data processing pipeline to construct dual-track dialogue datasets, facilitating scalable training and experimental validation. Experiments show that our model outperforms baselines, offering a solution for generating human-like spoken dialogues. Audio samples are available at https://tiamojames.github.io/DialoSpeech