Stage-Wise and Prior-Aware Neural Speech Phase Prediction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Fei, Ai, Yang, Du, Hui-Peng, Lu, Ye-Xin, Zheng, Rui-Chen, Ling, Zhen-Hua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910637297238016
author Liu, Fei
Ai, Yang
Du, Hui-Peng
Lu, Ye-Xin
Zheng, Rui-Chen
Ling, Zhen-Hua
author_facet Liu, Fei
Ai, Yang
Du, Hui-Peng
Lu, Ye-Xin
Zheng, Rui-Chen
Ling, Zhen-Hua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stage-Wise and Prior-Aware Neural Speech Phase Prediction
Liu, Fei
Ai, Yang
Du, Hui-Peng
Lu, Ye-Xin
Zheng, Rui-Chen
Ling, Zhen-Hua
Sound
Artificial Intelligence
Audio and Speech Processing
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.
title Stage-Wise and Prior-Aware Neural Speech Phase Prediction
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2410.04990