End-to-end recurrent denoising autoencoder embeddings for speaker identification

Speech ‘in-the-wild’ is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of representation learning, we aim to design a recurrent denoising autoenc...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2021-11, Vol.33 (21), p.14429-14439
Main Authors: Rituerto-González, Esther, Peláez-Moreno, Carmen
Format: Article
Language:English
Subjects:
Artificial Intelligence
Audio equipment
Background noise
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Feedback loops
Image Processing and Computer Vision
Noise
Noise reduction
Optimization
Original Article
Probability and Statistics in Computer Science
Representations
Spectrograms
Speech recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Speech ‘in-the-wild’ is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of representation learning, we aim to design a recurrent denoising autoencoder that extracts robust speaker embeddings from noisy spectrograms to perform speaker identification. The end-to-end proposed architecture uses a feedback loop to encode information regarding the speaker into low-dimensional representations extracted by a spectrogram denoising autoencoder. We employ data augmentation techniques by additively corrupting clean speech with real-life environmental noise in a database containing real stressed speech. Our study presents that the joint optimization of both the denoiser and speaker identification modules outperforms independent optimization of both components under stress and noise distortions as well as handcrafted features.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-021-06083-7