# RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

arXiv: https://arxiv.org/abs/2404.03204 · HTML: https://mlsanity.com/paper/2404.03204/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 70 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [UniAudio: An Audio Foundation Model Toward Universal Audio Generation](https://mlsanity.com/paper/2310.00704/) (2023)
- [VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation](https://mlsanity.com/paper/2305.16107/) (2023)
- [Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling](https://mlsanity.com/paper/2010.04301/) (2020)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [MultiSpeech: Multi-Speaker Text to Speech with Transformer](https://mlsanity.com/paper/2006.04664/) (2020)
- [Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS](https://mlsanity.com/paper/1906.00672/) (2019)
- [Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/1904.03446/) (2019)
- [VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech](https://mlsanity.com/paper/2401.14321/) (2024)

## Built on by (most cited first, 26 of 26)

- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [Autoregressive Speech Synthesis without Vector Quantization](https://mlsanity.com/paper/2407.08551/) (2024)
- [A Survey on (M)LLM-Based GUI Agents](https://mlsanity.com/paper/2504.13865/) (2025)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment](https://mlsanity.com/paper/2406.07855/) (2024)
- [Preference Alignment Improves Language Model-Based TTS](https://mlsanity.com/paper/2409.12403/) (2024)
- [Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback](https://mlsanity.com/paper/2406.00654/) (2024)
- [SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models](https://mlsanity.com/paper/2408.13893/) (2024)
- [TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling](https://mlsanity.com/paper/2504.07053/) (2025)
- [Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization](https://mlsanity.com/paper/2407.02243/) (2024)
- [FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching](https://mlsanity.com/paper/2502.11128/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [Voice Cloning: Comprehensive Survey](https://mlsanity.com/paper/2505.00579/) (2025)
- [Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy](https://mlsanity.com/paper/2506.22023/) (2025)
- [Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations](https://mlsanity.com/paper/2503.12115/) (2025)
- [Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling](https://mlsanity.com/paper/2505.19669/) (2025)
- [Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?](https://mlsanity.com/paper/2408.10853/) (2024)
- [Text-to-Speech for Unseen Speakers via Low-Complexity Discrete Unit-Based Frame Selection](https://mlsanity.com/paper/2408.17432/) (2024)
- [Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation](https://mlsanity.com/paper/2409.11003/) (2024)
- [Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis](https://mlsanity.com/paper/2410.23320/) (2024)
- [Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis](https://mlsanity.com/paper/2609.03992/) (2026)
- [Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech](https://mlsanity.com/paper/2609.11545/) (2026)
- [Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech](https://mlsanity.com/paper/2609.36974/) (2026)

## Abstract (arXiv)

We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor robustness, such as unstable prosody (weird pitch and rhythm/duration) and a high word error rate (WER), due to the autoregressive prediction style of language models. The core idea behind RALL-E is chain-of-thought (CoT) prompting, which decomposes the task into simpler steps to enhance the robustness of LLM-based TTS. To accomplish this idea, RALL-E first predicts prosody features (pitch and duration) of the input text and uses them as intermediate conditions to predict speech tokens in a CoT style. Second, RALL-E utilizes the predicted duration prompt to guide the computing of self-attention weights in Transformer to enforce the model to focus on the corresponding phonemes and prosody features when predicting speech tokens. Results of comprehensive objective and subjective evaluations demonstrate that, compared to a powerful baseline method VALL-E, RALL-E significantly improves the WER of zero-shot TTS from 5.6% (without reranking) and 1.7% (with reranking) to 2.5% and 1.0%, respectively. Furthermore, we demonstrate that RALL-E correctly synthesizes sentences that are hard for VALL-E and reduces the error rate from 68% to 4%.