IEEE/ACM Transactions on Audio Speech and Language Processing · 2015 · 20 citations · 57 references
ComputingComputer ScienceMachine LearningNatural Language ProcessingPsychoacousticsDeep LearningGenerative ModelingNeural NetworksPattern RecognitionSource SeparationSpeech RecognitionAutoencodersBandwidthBandwidth ExtensionBandwidth Extension TechniquesRestricted Boltzmann MachinesSound Source SeparationSpeaker-dependent Speech AnalysisSpeech Reconstruction In Noise
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 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> 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.
57
A Fast Learning Algorithm for Deep Belief Nets
Geoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh · Neural Computation · 2006 · 16.4K citations
Learning the parts of objects by non-negative matrix factorization
Daniel D. Lee, H. Sebastian Seung · Nature · 1999 · 14.1K citations