Audio-noise Power Spectral Density Estimation Using Long Short-term Memory - Archive ouverte HAL Access content directly
Journal Articles IEEE Signal Processing Letters Year : 2019

Audio-noise Power Spectral Density Estimation Using Long Short-term Memory

(1) , (1) , (2, 1) , (1)
1
2

Abstract

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to all frequency bands is trained, which processes each frequency band individually by mapping the noisy STFT magnitude sequence to its corresponding noise PSD sequence. Unlike deep-learning-based speech enhancement methods that learn the full-band spectral structure of speech segments, the proposed method exploits the sub-band STFT magnitude evolution of noise with a long time dependency, in the spirit of the unsupervised noise estimators described in the literature. Speaker-and speech-independent experiments with different types of noise show that the proposed method outperforms the unsupervised estimators, and generalizes well to noise types that are not present in the training set.
Fichier principal
Vignette du fichier
noise_psd.pdf (279.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02100059 , version 1 (15-04-2019)

Identifiers

Cite

Xiaofei Li, Simon Leglaive, Laurent Girin, Radu Horaud. Audio-noise Power Spectral Density Estimation Using Long Short-term Memory. IEEE Signal Processing Letters, 2019, 26 (6), pp.918-922. ⟨10.1109/LSP.2019.2911879⟩. ⟨hal-02100059⟩
166 View
753 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More