Toward Complex-Valued Neural Networks for Waveform Generation

• URL: http://arxiv.org/abs/2603.11589v1
• Date: Thu, 12 Mar 2026 06:24:11 GMT
• Title: Toward Complex-Valued Neural Networks for Waveform Generation
• Abstract summary: We present ComVo, a complex-valued neural vocoder whose generator and discriminator use native complex arithmetic.<n>Experiments demonstrate that ComVo achieves higher quality than comparable real-valued baselines, and that its block-matrix scheme reduces training time by 25%.
• Score: 49.128847336227636
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural vocoders have recently advanced waveform generation, yielding natural and expressive audio. Among these approaches, iSTFT-based vocoders have recently gained attention. They predict a complex-valued spectrogram and then synthesize the waveform via iSTFT, thereby avoiding learned upsampling stages that can increase computational cost. However, current approaches use real-valued networks that process the real and imaginary parts independently. This separation limits their ability to capture the inherent structure of complex spectrograms. We present ComVo, a Complex-valued neural Vocoder whose generator and discriminator use native complex arithmetic. This enables an adversarial training framework that provides structured feedback in complex-valued representations. To guide phase transformations in a structured manner, we introduce phase quantization, which discretizes phase values and regularizes the training process. Finally, we propose a block-matrix computation scheme to improve training efficiency by reducing redundant operations. Experiments demonstrate that ComVo achieves higher synthesis quality than comparable real-valued baselines, and that its block-matrix scheme reduces training time by 25%. Audio samples and code are available at https://hs-oh-prml.github.io/ComVo/.

Related papers

• Self-Supervised Learning via Flow-Guided Neural Operator on Time-Series Data [57.85958428020496]
  Flow-Guided Neural Operator (FGNO) is a novel framework combining operator learning with flow matching for SSL training.<n>FGNO learns mappings in functional spaces by using Short-Time Fourier Transform to unify different time resolutions.<n>Unlike prior generative SSL methods that use noisy inputs during inference, we propose using clean inputs for representation extraction while learning representations with noise.
  arXiv  Detail & Related papers  (2026-02-12T18:54:57Z)
• Representation-Regularized Convolutional Audio Transformer for Audio Understanding [53.092757178419355]
  bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge.<n>We propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2026-01-29T12:16:19Z)
• Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks [1.5124439914522694]
  We introduce a theoretical framework that explains the capacity property of sinusoidal networks.<n>We show how its layer compositions produce a large number of new frequencies expressed as integer combinations of the input frequencies.<n>Our method, referred to as TUNER, greatly improves the stability and convergence of sinusoidal INR training, leading to detailed reconstructions.
  arXiv  Detail & Related papers  (2024-07-30T18:24:46Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• An investigation of the reconstruction capacity of stacked convolutional autoencoders for log-mel-spectrograms [2.3204178451683264]
  In audio processing applications, the generation of expressive sounds based on high-level representations demonstrates a high demand. Modern algorithms, such as neural networks, have inspired the development of expressive synthesizers based on musical instrument compression. This study investigates the use of stacked convolutional autoencoders for the compression of time-frequency audio representations for a variety of instruments for a single pitch.
  arXiv  Detail & Related papers  (2023-01-18T17:19:04Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform [38.271530231451834]
  A mel-spectrogram vocoder must solve three inverse problems: recovery of the original-scale magnitude spectrogram, phase reconstruction, and frequency-to-time conversion. A typical convolutional mel-spectrogram vocoder solves these problems jointly and implicitly using a convolutional neural network. We propose iSTFTNet, which replaces some output-side layers of the mel-spectrogram vocoder with the inverse short-time Fourier transform.
  arXiv  Detail & Related papers  (2022-03-04T16:05:48Z)
• TCTN: A 3D-Temporal Convolutional Transformer Network for Spatiotemporal Predictive Learning [1.952097552284465]
  We propose an algorithm named 3D-temporal convolutional transformer (TCTN), where a transformer-based encoder with temporal convolutional layers is employed to capture short-term and long-term dependencies. Our proposed algorithm can be easy to implement and trained much faster compared with RNN-based methods thanks to the parallel mechanism of Transformer.
  arXiv  Detail & Related papers  (2021-12-02T10:05:01Z)
• Computational optimization of convolutional neural networks using separated filters architecture [69.73393478582027]
  We consider a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Use of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding.
  arXiv  Detail & Related papers  (2020-02-18T17:42:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.