# ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech

arXiv: https://arxiv.org/abs/1807.07281 · HTML: https://mlsanity.com/paper/1807.07281/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 30 of 70)

- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [Diff-TTS: A Denoising Diffusion Model for Text-to-Speech](https://mlsanity.com/paper/2104.01409/) (2021)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [DreamHuman: Animatable 3D Avatars from Text](https://mlsanity.com/paper/2306.09329/) (2023)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [RAVE: A variational autoencoder for fast and high-quality neural audio synthesis](https://mlsanity.com/paper/2111.05011/) (2021)
- [A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI](https://mlsanity.com/paper/2303.13336/) (2023)
- [WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis](https://mlsanity.com/paper/2106.09660/) (2021)
- [Neural Dubber: Dubbing for Videos According to Scripts](https://mlsanity.com/paper/2110.08243/) (2021)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows](https://mlsanity.com/paper/2110.11377/) (2021)
- [iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform](https://mlsanity.com/paper/2203.02395/) (2022)
- [Learning to Dub Movies via Hierarchical Prosody Models](https://mlsanity.com/paper/2212.04054/) (2022)
- [Universal Neural Vocoding with Parallel WaveNet](https://mlsanity.com/paper/2102.01106/) (2021)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics](https://mlsanity.com/paper/2105.08164/) (2021)
- [High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency](https://mlsanity.com/paper/2111.09052/) (2021)
- [AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person](https://mlsanity.com/paper/2108.04325/) (2021)
- [GAN Vocoder: Multi-Resolution Discriminator Is All You Need](https://mlsanity.com/paper/2103.05236/) (2021)
- [Catch-A-Waveform: Learning to Generate Audio from a Single Short Example](https://mlsanity.com/paper/2106.06426/) (2021)
- [The Age of Synthetic Realities: Challenges and Opportunities](https://mlsanity.com/paper/2306.11503/) (2023)
- [Speech Denoising in the Waveform Domain with Self-Attention](https://mlsanity.com/paper/2202.07790/) (2022)
- [VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention](https://mlsanity.com/paper/2102.06431/) (2021)
- [Emotional Prosody Control for Speech Generation](https://mlsanity.com/paper/2111.04730/) (2021)
- [PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation](https://mlsanity.com/paper/2408.07547/) (2024)

## Abstract (arXiv)

In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a regularized KL divergence between their highly-peaked output distributions. Our method computes the KL divergence in closed-form, which simplifies the training algorithm and provides very efficient distillation. In addition, we introduce the first text-to-wave neural architecture for speech synthesis, which is fully convolutional and enables fast end-to-end training from scratch. It significantly outperforms the previous pipeline that connects a text-to-spectrogram model to a separately trained WaveNet (Ping et al., 2018). We also successfully distill a parallel waveform synthesizer conditioned on the hidden representation in this end-to-end model.