Deep Learning for Audio Signal Processing
Autor: | Jan Schlüter, Hendrik Purwins, Shuo-Yiin Chang, Tuomas Virtanen, Bo Li, Tara N. Sainath |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer science Speech recognition Machine Learning (stat.ML) 02 engineering and technology computer.software_genre Convolutional neural network Computer Science - Sound H.5.1 Audio and Speech Processing (eess.AS) Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Source separation Feature (machine learning) FOS: Electrical engineering electronic engineering information engineering Music information retrieval Hidden Markov models Electrical and Electronic Engineering Audio signal processing Artificial neural network business.industry I.2.6 Deep learning Sound detection 020206 networking & telecommunications Computational modeling Convolution Signal Processing Task analysis Artificial intelligence business computer Music Electrical Engineering and Systems Science - Audio and Speech Processing |
Zdroj: | IEEE Journal of Selected Topics in Signal Processing Purwins, H, Li, B, Virtanen, T, Schlüter, J, Chang, S-Y & Sainath, T 2019, ' Deep Learning for Audio Signal Processing ', IEEE Journal of Selected Topics in Signal Processing, vol. 13, no. 2, 8678825, pp. 206-219 . https://doi.org/10.1109/JSTSP.2019.2908700 |
Popis: | Given the recent surge in developments of deep learning, this article 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. 15 pages, 2 pdf figures |
Databáze: | OpenAIRE |
Externí odkaz: |