# Multi-modal Adversarial Training for Zero-Shot Voice Cloning

arXiv: https://arxiv.org/abs/2408.15916 · HTML: https://mlsanity.com/paper/2408.15916/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 28 Aug 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus](https://mlsanity.com/paper/2305.18802/) (2023)
- [High Fidelity Speech Synthesis with Adversarial Networks](https://mlsanity.com/paper/1909.11646/) (2019)
- [Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context](https://mlsanity.com/paper/2309.08105/) (2023)
- [Revisiting Over-Smoothness in Text to Speech](https://mlsanity.com/paper/2202.13066/) (2022)
- [E3 TTS: Easy End-to-End Diffusion-based Text to Speech](https://mlsanity.com/paper/2311.00945/) (2023)
- [Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis](https://mlsanity.com/paper/2012.07267/) (2020)
- [VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design](https://mlsanity.com/paper/2307.16430/) (2023)
- [DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021](https://mlsanity.com/paper/2110.12612/) (2021)
- [GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis](https://mlsanity.com/paper/2106.15153/) (2021)
- [GAZEV: GAN-Based Zero-Shot Voice Conversion over Non-parallel Speech Corpus](https://mlsanity.com/paper/2010.12788/) (2020)
- [Reducing over-smoothness in speech synthesis using Generative Adversarial Networks](https://mlsanity.com/paper/1810.10989/) (2018)
- [Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2305.16749/) (2023)

## Built on by (most cited first, 2 of 2)

- [StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion](https://mlsanity.com/paper/2409.10058/) (2024)
- [DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2410.11097/) (2024)

## Abstract (arXiv)

A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem is magnified for zero-shot voice cloning, a task that requires training data with high variance in speaking styles. We build off of recent works which have used Generative Advsarial Networks (GAN) by proposing a Transformer encoder-decoder architecture to conditionally discriminates between real and generated speech features. The discriminator is used in a training pipeline that improves both the acoustic and prosodic features of a TTS model. We introduce our novel adversarial training technique by applying it to a FastSpeech2 acoustic model and training on Libriheavy, a large multi-speaker dataset, for the task of zero-shot voice cloning. Our model achieves improvements over the baseline in terms of speech quality and speaker similarity. Audio examples from our system are available online.