mlsanityData to 7 Oct 2026

FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder

arXiv 2401.10032 ↗First posted 18 Jan 2024eess.AS cs.AI eess.SPcited by 11

Not on the map. Why?

Abstract (arXiv)

The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes a complicated waveform into sub-band wavelets, which helps FreGrad to operate on a simple and concise feature space, (2) We design a frequency-aware dilated convolution that elevates frequency awareness, resulting in generating speech with accurate frequency information, and (3) We introduce a bag of tricks that boosts the generation quality of the proposed model. In our experiments, FreGrad achieves 3.7 times faster training time and 2.2 times faster inference speed compared to our baseline while reducing the model size by 0.6 times (only 1.78M parameters) without sacrificing the output quality. Audio samples are available at: https://mm.kaist.ac.kr/projects/FreGrad.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 25 of its 32 references that are in the map. First posted on arXiv 18 Jan 2024.

Builds on

25 of 32 references.

References · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  5. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  6. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  7. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  8. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  9. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  10. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  11. 2019AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Losscited by 189
  12. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
13 more
  1. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
  2. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 114
  3. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  4. 2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
  5. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 78
  6. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesiscited by 64
  7. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  8. 2022SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shapingcited by 37
  9. 2020DeepSinger: Singing Voice Synthesis with Data Mined From the Webcited by 32
  10. 2022iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transformcited by 30
  11. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Trainingcited by 28
  12. 2021Fre-GAN: Adversarial Frequency-consistent Audio Synthesiscited by 24
  13. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocodercited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 2.

11 papers.

  1. 2024Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decodingcited by 10
  2. 2024VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesiscited by 10
  3. 2024RFWave: Multi-band Rectified Flow for Audio Waveform Reconstructioncited by 9
  4. 2024Text-To-Speech Synthesis In The Wildcited by 6
  5. 2025Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generationcited by 4
  6. 2024CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generationcited by 0
  7. 2025Spiking Vocos: An Energy-Efficient Neural Vocodercited by 0
  8. 2025BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspectivecited by 0
  9. 2025GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesiscited by 0
  10. 2026WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Modelscited by 0
  11. 2026Exploring Efficient Waveform Diffusion Models for Foley Sound Generationcited by 0