A primer on deep learning architectures and applications in speech processing

Tokunbo Ogunfunmi, Ravi Prakash Ramachandran, Roberto Togneri, Yuanjun Zhao, Xianjun Xia

Research output: Contribution to journalReview article

Abstract

In the recent past years, deep-learning-based machine learning methods have demonstrated remarkable success for a wide range of learning tasks in multiple domains. They are suitable for complex classification and regression problems in applications such as computer vision, speech recognition and other pattern analysis branches. The purpose of this article is to contribute a timely review and introduction of state-of-the-art and popular discriminative DNN, CNN and RNN deep learning techniques, the basic framework and algorithms, hardware implementations, applications in speech, and the overall benefits of deep learning.

Original languageEnglish
Pages (from-to)3406–3432
JournalCircuits, Systems, and Signal Processing
Volume38
Issue number8
DOIs
Publication statusPublished - Aug 2019

Fingerprint

Speech Processing
Speech processing
Speech recognition
Computer vision
Pattern Analysis
Learning systems
Hardware Implementation
Speech Recognition
Computer Vision
Hardware
Machine Learning
Branch
Regression
Learning
Architecture
Deep learning
Range of data

Cite this

Ogunfunmi, Tokunbo ; Ramachandran, Ravi Prakash ; Togneri, Roberto ; Zhao, Yuanjun ; Xia, Xianjun. / A primer on deep learning architectures and applications in speech processing. In: Circuits, Systems, and Signal Processing. 2019 ; Vol. 38, No. 8. pp. 3406–3432.
@article{fbda62ca8da344d4bfe60e369a62e8d4,
title = "A primer on deep learning architectures and applications in speech processing",
abstract = "In the recent past years, deep-learning-based machine learning methods have demonstrated remarkable success for a wide range of learning tasks in multiple domains. They are suitable for complex classification and regression problems in applications such as computer vision, speech recognition and other pattern analysis branches. The purpose of this article is to contribute a timely review and introduction of state-of-the-art and popular discriminative DNN, CNN and RNN deep learning techniques, the basic framework and algorithms, hardware implementations, applications in speech, and the overall benefits of deep learning.",
keywords = "Deep learning, Discriminative algorithms, Signal processing",
author = "Tokunbo Ogunfunmi and Ramachandran, {Ravi Prakash} and Roberto Togneri and Yuanjun Zhao and Xianjun Xia",
year = "2019",
month = "8",
doi = "10.1007/s00034-019-01157-3",
language = "English",
volume = "38",
pages = "3406–3432",
journal = "Circuits, Systems and Signal Processing",
issn = "0278-081X",
publisher = "Springer",
number = "8",

}

A primer on deep learning architectures and applications in speech processing. / Ogunfunmi, Tokunbo; Ramachandran, Ravi Prakash; Togneri, Roberto; Zhao, Yuanjun; Xia, Xianjun.

In: Circuits, Systems, and Signal Processing, Vol. 38, No. 8, 08.2019, p. 3406–3432.

Research output: Contribution to journalReview article

TY - JOUR

T1 - A primer on deep learning architectures and applications in speech processing

AU - Ogunfunmi, Tokunbo

AU - Ramachandran, Ravi Prakash

AU - Togneri, Roberto

AU - Zhao, Yuanjun

AU - Xia, Xianjun

PY - 2019/8

Y1 - 2019/8

N2 - In the recent past years, deep-learning-based machine learning methods have demonstrated remarkable success for a wide range of learning tasks in multiple domains. They are suitable for complex classification and regression problems in applications such as computer vision, speech recognition and other pattern analysis branches. The purpose of this article is to contribute a timely review and introduction of state-of-the-art and popular discriminative DNN, CNN and RNN deep learning techniques, the basic framework and algorithms, hardware implementations, applications in speech, and the overall benefits of deep learning.

AB - In the recent past years, deep-learning-based machine learning methods have demonstrated remarkable success for a wide range of learning tasks in multiple domains. They are suitable for complex classification and regression problems in applications such as computer vision, speech recognition and other pattern analysis branches. The purpose of this article is to contribute a timely review and introduction of state-of-the-art and popular discriminative DNN, CNN and RNN deep learning techniques, the basic framework and algorithms, hardware implementations, applications in speech, and the overall benefits of deep learning.

KW - Deep learning

KW - Discriminative algorithms

KW - Signal processing

UR - http://www.scopus.com/inward/record.url?scp=85067281924&partnerID=8YFLogxK

U2 - 10.1007/s00034-019-01157-3

DO - 10.1007/s00034-019-01157-3

M3 - Review article

VL - 38

SP - 3406

EP - 3432

JO - Circuits, Systems and Signal Processing

JF - Circuits, Systems and Signal Processing

SN - 0278-081X

IS - 8

ER -