# Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses

arXiv: https://arxiv.org/abs/2211.15974 · HTML: https://mlsanity.com/paper/2211.15974/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2022.

## Built on by (most cited first, 11 of 11)

- [xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2501.06146/) (2025)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement](https://mlsanity.com/paper/2507.00966/) (2025)
- [Stage-Wise and Prior-Aware Neural Speech Phase Prediction](https://mlsanity.com/paper/2410.04990/) (2024)
- [Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs](https://mlsanity.com/paper/2505.24684/) (2025)
- [SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsampling](https://mlsanity.com/paper/2506.22321/) (2025)
- [EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement](https://mlsanity.com/paper/2508.14525/) (2025)
- [When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms](https://mlsanity.com/paper/2606.10868/) (2026)
- [QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement](https://mlsanity.com/paper/2606.18611/) (2026)
- [Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model](https://mlsanity.com/paper/2610.06817/) (2026)

## Abstract (arXiv)

This paper presents a novel speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra by neural networks. The proposed model is a cascade of a residual convolutional network and a parallel estimation architecture. The parallel estimation architecture is composed of two parallel linear convolutional layers and a phase calculation formula, imitating the process of calculating the phase spectra from the real and imaginary parts of complex spectra and strictly restricting the predicted phase values to the principal value interval. To avoid the error expansion issue caused by phase wrapping, we design anti-wrapping training losses defined between the predicted wrapped phase spectra and natural ones by activating the instantaneous phase error, group delay error and instantaneous angular frequency error using an anti-wrapping function. Experimental results show that our proposed neural speech phase prediction model outperforms the iterative Griffin-Lim algorithm and other neural network-based method, in terms of both reconstructed speech quality and generation speed.