Deep Learning for Audio Signal Processing

Given the recent surge in developments of deep learning, this paper provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences betwee...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in signal processing Vol. 13; no. 2; pp. 206 - 219
Main Authors: Purwins, Hendrik, Li, Bo, Virtanen, Tuomas, Schluter, Jan, Chang, Shuo-Yiin, Sainath, Tara
Format: Journal Article
Language:English
Published: New York IEEE 01.05.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Acknowledgment
Artificial neural networks
Audio data
audio enhancement
Automatic speech recognition
Background noise
Computational modeling
Computer architecture
Computer memory
connectionist temporal memory
Convolution
Data mining
Deep learning
Domains
environmental sounds
Hidden Markov models
Information retrieval
Learning
Localization
Music
music information retrieval
Neural networks
Retrieval
Short term memory
Signal processing
Sound processing
Source separation
Speech
Speech recognition
State-of-the-art reviews
Synthesis
Task analysis
Tracking
Transformation
Variants
Voice recognition
ISSN:1932-4553, 1941-0484
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Given the recent surge in developments of deep learning, this paper provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variants of the long short-term memory architecture, as well as more audio-specific neural network models. Subsequently, prominent deep learning application areas are covered, i.e., audio recognition (automatic speech recognition, music information retrieval, environmental sound detection, localization and tracking) and synthesis and transformation (source separation, audio enhancement, generative models for speech, sound, and music synthesis). Finally, key issues and future questions regarding deep learning applied to audio signal processing are identified.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1932-4553
1941-0484
DOI:10.1109/JSTSP.2019.2908700