Speaker recognition with hybrid features from a deep belief network

Learning representation from audio data has shown advantages over the handcrafted features such as mel-frequency cepstral coefficients (MFCCs) in many audio applications. In most of the representation learning approaches, the connectionist systems have been used to learn and extract latent features...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2018-03, Vol.29 (6), p.13-19
Main Authors: Ali, Hazrat, Tran, Son N., Benetos, Emmanouil, d’Avila Garcez, Artur S.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Audio data
Audio equipment
Belief networks
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Counting
Data Mining and Knowledge Discovery
Feature extraction
Feature recognition
Image Processing and Computer Vision
Original Article
Probability and Statistics in Computer Science
Representations
Scripts
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:Learning representation from audio data has shown advantages over the handcrafted features such as mel-frequency cepstral coefficients (MFCCs) in many audio applications. In most of the representation learning approaches, the connectionist systems have been used to learn and extract latent features from the fixed length data. In this paper, we propose an approach to combine the learned features and the MFCC features for speaker recognition task, which can be applied to audio scripts of different lengths. In particular, we study the use of features from different levels of deep belief network for quantizing the audio data into vectors of audio word counts. These vectors represent the audio scripts of different lengths that make them easier to train a classifier. We show in the experiment that the audio word count vectors generated from mixture of DBN features at different layers give better performance than the MFCC features. We also can achieve further improvement by combining the audio word count vector and the MFCC features.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-016-2501-7