mlsanityData to 14 Oct 2026

Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks

arXiv 1808.06719 ↗First posted 20 Aug 2018cs.SD cs.LG eess.AScited by 22

Not on the map. Why?

Abstract (arXiv)

We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN achieves more than an order of magnitude higher compute intensity than commonly-used iterative algorithms like Griffin-Lim, yielding efficient utilization for modern multi-core processors, and very fast (more than 300x real-time) waveform synthesis. For training of MCNN, we use a large-scale speech recognition dataset and losses defined on waveforms that are related to perceptual audio quality. We demonstrate that MCNN constitutes a very promising approach for high-quality speech synthesis, without any iterative algorithms or autoregression in computations.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 4; 2024: 6; 2025: 4; 2026: 1.

22 papers.

Sort:

By area:

  1. 2021A Survey on Neural Speech Synthesiscited by 184
  2. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  3. 2021Universal Neural Vocoding with Parallel WaveNetcited by 25
  4. 2022On loss functions and evaluation metrics for music source separationcited by 17
  5. 2021Catch-A-Waveform: Learning to Generate Audio from a Single Short Examplecited by 15
  6. 2022Audio representations for deep learning in sound synthesis: A reviewcited by 9
  7. 2024RFWave: Multi-band Rectified Flow for Audio Waveform Reconstructioncited by 9
  8. 2024NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fieldscited by 9
  9. 2023Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transportcited by 8
  10. 2023Msanii: High Fidelity Music Synthesis on a Shoestring Budgetcited by 6
  11. 2024Synthesizer Sound Matching Using Audio Spectrogram Transformerscited by 4
  12. 2023Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancementcited by 2
10 more
  1. 2023ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learningcited by 2
  2. 2022EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Acceleratorscited by 1
  3. 2024RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attentioncited by 1
  4. 2024Sines, Transient, Noise Neural Modeling of Piano Notescited by 1
  5. 2025Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restorationcited by 1
  6. 2025Representation of perceived prosodic similarity of conversational feedbackcited by 1
  7. 2024SPEAR: Receiver-to-Receiver Acoustic Neural Warping Fieldcited by 0
  8. 2025Frequency-Aware Masked Autoencoders for Human Activity Recognition using Accelerometerscited by 0
  9. 2025Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theoremcited by 0
  10. 2026Challenges of Multi-Speaker Extraction for Real Conversational Speech Enhancementcited by 0