TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Deep Learning for Audio Signal Processing

Tutkimustuotosvertaisarvioitu

Standard

Deep Learning for Audio Signal Processing. / Purwins, Hendrik; Li, Bo; Virtanen, Tuomas; Schlüter, Jan; Chang, Shuo Yiin; Sainath, Tara.

julkaisussa: IEEE Journal on Selected Topics in Signal Processing, Vuosikerta 13, Nro 2, 01.05.2019, s. 206-219.

Tutkimustuotosvertaisarvioitu

Harvard

Purwins, H, Li, B, Virtanen, T, Schlüter, J, Chang, SY & Sainath, T 2019, 'Deep Learning for Audio Signal Processing', IEEE Journal on Selected Topics in Signal Processing, Vuosikerta. 13, Nro 2, Sivut 206-219. https://doi.org/10.1109/JSTSP.2019.2908700

APA

Purwins, H., Li, B., Virtanen, T., Schlüter, J., Chang, S. Y., & Sainath, T. (2019). Deep Learning for Audio Signal Processing. IEEE Journal on Selected Topics in Signal Processing, 13(2), 206-219. https://doi.org/10.1109/JSTSP.2019.2908700

Vancouver

Purwins H, Li B, Virtanen T, Schlüter J, Chang SY, Sainath T. Deep Learning for Audio Signal Processing. IEEE Journal on Selected Topics in Signal Processing. 2019 touko 1;13(2):206-219. https://doi.org/10.1109/JSTSP.2019.2908700

Author

Purwins, Hendrik ; Li, Bo ; Virtanen, Tuomas ; Schlüter, Jan ; Chang, Shuo Yiin ; Sainath, Tara. / Deep Learning for Audio Signal Processing. Julkaisussa: IEEE Journal on Selected Topics in Signal Processing. 2019 ; Vuosikerta 13, Nro 2. Sivut 206-219.

Bibtex - Lataa

@article{054b62d66ef84ddf9f8e6346d9931860,
title = "Deep Learning for Audio Signal Processing",
abstract = "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.",
keywords = "audio enhancement, automatic speech recognition, connectionist temporal memory, Deep learning, environmental sounds, music information retrieval, source separation",
author = "Hendrik Purwins and Bo Li and Tuomas Virtanen and Jan Schl{\"u}ter and Chang, {Shuo Yiin} and Tara Sainath",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/JSTSP.2019.2908700",
language = "English",
volume = "13",
pages = "206--219",
journal = "IEEE Journal of Selected Topics in Signal Processing",
issn = "1932-4553",
publisher = "Institute of Electrical and Electronics Engineers",
number = "2",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Deep Learning for Audio Signal Processing

AU - Purwins, Hendrik

AU - Li, Bo

AU - Virtanen, Tuomas

AU - Schlüter, Jan

AU - Chang, Shuo Yiin

AU - Sainath, Tara

PY - 2019/5/1

Y1 - 2019/5/1

N2 - 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.

AB - 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.

KW - audio enhancement

KW - automatic speech recognition

KW - connectionist temporal memory

KW - Deep learning

KW - environmental sounds

KW - music information retrieval

KW - source separation

U2 - 10.1109/JSTSP.2019.2908700

DO - 10.1109/JSTSP.2019.2908700

M3 - Article

VL - 13

SP - 206

EP - 219

JO - IEEE Journal of Selected Topics in Signal Processing

JF - IEEE Journal of Selected Topics in Signal Processing

SN - 1932-4553

IS - 2

ER -