Medizinische Universität Graz - Research portal
Selected Publication:
SHR Neuro Cancer Cardio Lipid Metab Microb
Zohrer, M; Peharz, R; Pernkopf, F; .
Representation Learning for Single-Channel Source Separation and Bandwidth Extension.
IEEE-ACM TRANS AUDIO SPEECH L. 2015; 23(12): 2398-2409.
Doi: 10.1109/TASLP.2015.2470560
Web of Science
FullText
FullText_MUG
- Co-authors Med Uni Graz
- Peharz Robert
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- In this paper, we use deep representation learning for model-based single-channel source separation (SCSS) and artificial bandwidth extension (ABE). Both tasks are ill-posed and source-specific prior knowledge is required. In addition to well-known generative models such as restricted Boltzmann machines and higher order contractive autoencoders two recently introduced deep models, namely generative stochastic networks (GSNs) and sum-product networks (SPNs), are used for learning spectrogram representations. For SCSS we evaluate the deep architectures on data of the 2 CHiME speech separation challenge and provide results for a speaker dependent, a speaker independent, a matched noise condition and an unmatched noise condition task. GSNs obtain the best PESQ and overall perceptual score on average in all four tasks. Similarly, frame-wise GSNs are able to reconstruct the missing frequency bands in ABE best, measured in frequency-domain segmental SNR. They outperform SPNs embedded in hidden Markov models and the other representation models significantly.
- Find related publications in this database (Keywords)
- Bandwidth extension
- deep neural networks (DNNs)
- generative stochastic networks
- representation learning
- single-channel source separation (SCSS)
- sum-product networks