# Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling

arXiv: https://arxiv.org/abs/2509.22062 · HTML: https://mlsanity.com/paper/2509.22062/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models.
- Builds on 45 of its 48 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

## Builds on (most cited first, 30 of 45)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://mlsanity.com/paper/2406.18009/) (2024)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)

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

- [PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models](https://mlsanity.com/paper/2610.26891/) (2026)

## Abstract (arXiv)

Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation of this LLM-based paradigm is the discretization of the continuous speech waveform into a sequence of discrete tokens by neural audio codec. However, single codebook modeling is well suited to text LLMs, but suffers from significant information loss; hierarchical acoustic tokens, typically generated via Residual Vector Quantization (RVQ), often lack explicit semantic structure, placing a heavy learning burden on the model. Furthermore, the autoregressive process is inherently susceptible to error accumulation, which can degrade generation stability. To address these limitations, we propose CaT-TTS, a novel framework for robust and semantically-grounded zero-shot synthesis. First, we introduce S3Codec, a split RVQ codec that injects explicit linguistic features into its primary codebook via semantic distillation from a state-of-the-art ASR model, providing a structured representation that simplifies the learning task. Second, we propose an ``Understand-then-Generate'' dual-Transformer architecture that decouples comprehension from rendering. An initial ``Understanding'' Transformer models the cross-modal relationship between text and the audio's semantic tokens to form a high-level utterance plan. A subsequent ``Generation'' Transformer then executes this plan, autoregressively synthesizing hierarchical acoustic tokens. Finally, to enhance generation stability, we introduce Masked Audio Parallel Inference (MAPI), a nearly parameter-free inference strategy that dynamically guides the decoding process to mitigate local errors.