# Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization

arXiv: https://arxiv.org/abs/2608.11737 · HTML: https://mlsanity.com/paper/2608.11737/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 40 of its 41 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 40)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (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)
- [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)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [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)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://mlsanity.com/paper/2406.18009/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context](https://mlsanity.com/paper/2309.08105/) (2023)
- [FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications](https://mlsanity.com/paper/2409.03283/) (2024)
- [Autoregressive Speech Synthesis without Vector Quantization](https://mlsanity.com/paper/2407.08551/) (2024)
- [DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation](https://mlsanity.com/paper/2502.03930/) (2025)
- [LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models](https://mlsanity.com/paper/2310.02943/) (2023)
- [BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec](https://mlsanity.com/paper/2409.05377/) (2024)

## Abstract (arXiv)

In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning objectives. However, due to the inherent nature of speech, semantic and acoustic information cannot be completely decoupled, and ASR-based tokenizers discard acoustic details to focus on linguistic content; models relying on them usually struggle to achieve optimal speaker similarity. Furthermore, these tokenizers are optimized independently and lack direct supervision from downstream acoustic generation tasks. This isolated training creates a feature gap between the extracted discrete tokens and the continuous space required by acoustic models, fundamentally bottlenecking the upper bound of synthesis quality. To bridge this gap, we propose Phoenix TTS, a unified framework that tightly couples representation learning with generative acoustic modeling. Specifically, our speech tokenizer is optimized to reconstruct self-supervised features to maintain semantic richness, while simultaneously receiving direct supervision from a Flow Matching training loss. Through this joint training paradigm, the extracted discrete tokens successfully preserve essential semantic information and natively align with the feature space of the downstream Flow Matching model. Comprehensive evaluations highlight the efficiency and effectiveness of Phoenix TTS. Trained on 110K hours of data, the system achieves excellent speech intelligibility, yielding WER that consistently falls below that of ground-truth recordings. Simultaneously, it maintains robust zero-shot speaker similarity, rivaling or outperforming several prominent large-scale baselines. Furthermore, as an advantageous byproduct of this unified training, the learned tokenizer can be seamlessly adapted to zero-shot voice conversion tasks without requiring task-specific fine-tuning.