Back to Search
Start Over
Guest Editorial: Algorithms and Architectures for Machine Learning Based Speech Processing.
- Source :
- Circuits, Systems & Signal Processing; Aug2019, Vol. 38 Issue 8, p3399-3405, 7p
- Publication Year :
- 2019
-
Abstract
- Highlights from the article: Deep learning employs deep neural networks (DNNs), which are neural networks with more than one hidden layer, with recently developed initialization and training strategies using massive amounts of diverse data as examples. The paper provides an overview of recent approaches to deep learning as applied to a range of speech processing tasks, primarily for automatic speech recognition (ASR), but also text-to-speech and speaker, language, and emotion recognition. The authors propose integrating deep neural network (DNN)-HMM technique with the HiLAM method where the state alignment information from the HiLAM is used to discriminatively train a DNN to further improve the system performance.
Details
- Language :
- English
- ISSN :
- 0278081X
- Volume :
- 38
- Issue :
- 8
- Database :
- Complementary Index
- Journal :
- Circuits, Systems & Signal Processing
- Publication Type :
- Academic Journal
- Accession number :
- 137338118
- Full Text :
- https://doi.org/10.1007/s00034-019-01161-7