# ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech

arXiv: https://arxiv.org/abs/2202.07816 · HTML: https://mlsanity.com/paper/2202.07816/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Latent Video Transformer](https://mlsanity.com/paper/2006.10704/) (2020)
- [Deep Voice: Real-time Neural Text-to-Speech](https://mlsanity.com/paper/1702.07825/) (2017)
- [Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning](https://mlsanity.com/paper/1710.07654/) (2017)
- [PortaSpeech: Portable and High-Quality Generative Text-to-Speech](https://mlsanity.com/paper/2109.15166/) (2021)
- [Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis](https://mlsanity.com/paper/1808.01410/) (2018)
- [Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis](https://mlsanity.com/paper/2012.07267/) (2020)
- [Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/1904.03446/) (2019)
- [Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis](https://mlsanity.com/paper/2011.06465/) (2020)
- [Word-Level Style Control for Expressive, Non-attentive Speech Synthesis](https://mlsanity.com/paper/2111.10173/) (2021)

## Built on by (most cited first, 22 of 22)

- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias](https://mlsanity.com/paper/2306.03509/) (2023)
- [FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec](https://mlsanity.com/paper/2309.07405/) (2023)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training](https://mlsanity.com/paper/2307.16549/) (2023)
- [Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art](https://mlsanity.com/paper/2308.16316/) (2023)
- [HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer](https://mlsanity.com/paper/2307.16171/) (2023)
- [Accompanied Singing Voice Synthesis with Fully Text-controlled Melody](https://mlsanity.com/paper/2407.02049/) (2024)
- [From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech](https://mlsanity.com/paper/2503.16956/) (2025)
- [CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation](https://mlsanity.com/paper/2310.11295/) (2023)
- [CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis](https://mlsanity.com/paper/2312.10358/) (2023)
- [PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modeling](https://mlsanity.com/paper/2306.07489/) (2023)
- [Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2305.16749/) (2023)
- [ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models](https://mlsanity.com/paper/2507.20091/) (2025)
- [Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting](https://mlsanity.com/paper/2412.20155/) (2024)
- [Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping](https://mlsanity.com/paper/2311.05844/) (2023)
- [Cross-Utterance Conditioned VAE for Speech Generation](https://mlsanity.com/paper/2309.04156/) (2023)
- [Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP](https://mlsanity.com/paper/2309.05423/) (2023)
- [MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt](https://mlsanity.com/paper/2505.18453/) (2025)
- [TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation](https://mlsanity.com/paper/2512.20296/) (2025)
- [Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis](https://mlsanity.com/paper/2211.01327/) (2022)
- [CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation](https://mlsanity.com/paper/2412.20048/) (2024)

## Abstract (arXiv)

Expressive text-to-speech (TTS) has become a hot research topic recently, mainly focusing on modeling prosody in speech. Prosody modeling has several challenges: 1) the extracted pitch used in previous prosody modeling works have inevitable errors, which hurts the prosody modeling; 2) different attributes of prosody (e.g., pitch, duration and energy) are dependent on each other and produce the natural prosody together; and 3) due to high variability of prosody and the limited amount of high-quality data for TTS training, the distribution of prosody cannot be fully shaped. To tackle these issues, we propose ProsoSpeech, which enhances the prosody using quantized latent vectors pre-trained on large-scale unpaired and low-quality text and speech data. Specifically, we first introduce a word-level prosody encoder, which quantizes the low-frequency band of the speech and compresses prosody attributes in the latent prosody vector (LPV). Then we introduce an LPV predictor, which predicts LPV given word sequence. We pre-train the LPV predictor on large-scale text and low-quality speech data and fine-tune it on the high-quality TTS dataset. Finally, our model can generate expressive speech conditioned on the predicted LPV. Experimental results show that ProsoSpeech can generate speech with richer prosody compared with baseline methods.