# Stage-Wise and Prior-Aware Neural Speech Phase Prediction

arXiv: https://arxiv.org/abs/2410.04990 · HTML: https://mlsanity.com/paper/2410.04990/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 7 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancement](https://mlsanity.com/paper/1910.06762/) (2019)
- [Adversarial Generation of Time-Frequency Features with application in audio synthesis](https://mlsanity.com/paper/1902.04072/) (2019)
- [Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses](https://mlsanity.com/paper/2211.15974/) (2022)
- [A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis](https://mlsanity.com/paper/1906.09573/) (2019)
- [Phase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network](https://mlsanity.com/paper/1807.03474/) (2018)
- [Deep Griffin-Lim Iteration](https://mlsanity.com/paper/1903.03971/) (2019)
- [Low-Latency Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses for Speech Generation Tasks](https://mlsanity.com/paper/2403.17378/) (2024)

## Abstract (arXiv)

This paper proposes a novel Stage-wise and Prior-aware Neural Speech Phase Prediction (SP-NSPP) model, which predicts the phase spectrum from input amplitude spectrum by two-stage neural networks. In the initial prior-construction stage, we preliminarily predict a rough prior phase spectrum from the amplitude spectrum. The subsequent refinement stage transforms the amplitude spectrum into a refined high-quality phase spectrum conditioned on the prior phase. Networks in both stages use ConvNeXt v2 blocks as the backbone and adopt adversarial training by innovatively introducing a phase spectrum discriminator (PSD). To further improve the continuity of the refined phase, we also incorporate a time-frequency integrated difference (TFID) loss in the refinement stage. Experimental results confirm that, compared to neural network-based no-prior phase prediction methods, the proposed SP-NSPP achieves higher phase prediction accuracy, thanks to introducing the coarse phase priors and diverse training criteria. Compared to iterative phase estimation algorithms, our proposed SP-NSPP does not require multiple rounds of staged iterations, resulting in higher generation efficiency.