2015 - IEEE Fellow For contributions to audio source separation and audio processing
Paris Smaragdis focuses on Artificial intelligence, Speech recognition, Pattern recognition, Source separation and Non-negative matrix factorization. His study on Artificial intelligence is mostly dedicated to connecting different topics, such as Audio visual. His study in Speech recognition is interdisciplinary in nature, drawing from both Channel, Independent component analysis, Noise and Separation.
His work in Pattern recognition covers topics such as Noise reduction which are related to areas like Regularization. His Source separation research includes themes of Artificial neural network, Speech denoising, Speech processing and Spectrogram. His studies deal with areas such as Speech enhancement and Wiener filter as well as Non-negative matrix factorization.
Artificial intelligence, Speech recognition, Pattern recognition, Source separation and Algorithm are his primary areas of study. The various areas that Paris Smaragdis examines in his Artificial intelligence study include Non-negative matrix factorization and Computer vision. His Speech recognition research is multidisciplinary, incorporating elements of Acoustics, Audio signal processing, Audio signal and Signal processing.
His Pattern recognition study combines topics from a wide range of disciplines, such as Channel, Probabilistic logic, Speech enhancement, Noise and Noise reduction. Paris Smaragdis has included themes like Artificial neural network, Discriminative model, Markov chain and Speech processing in his Source separation study. Paris Smaragdis has researched Algorithm in several fields, including Fourier transform and Blind signal separation.
His main research concerns Artificial intelligence, Artificial neural network, Source separation, Algorithm and Speech recognition. His Artificial intelligence research incorporates themes from Machine learning and Pattern recognition. The concepts of his Pattern recognition study are interwoven with issues in Time domain, Column vector and Cluster analysis.
His Source separation research is multidisciplinary, relying on both Convergence, Waveform and Non-negative matrix factorization. He works mostly in the field of Algorithm, limiting it down to concerns involving Fourier transform and, occasionally, Gradient descent, Basis function and Frequency domain. His primary area of study in Speech recognition is in the field of Intelligibility.
His primary areas of investigation include Artificial neural network, Source separation, Artificial intelligence, Algorithm and Speech recognition. His Source separation study integrates concerns from other disciplines, such as Waveform and Spectrogram. Artificial intelligence and Pattern recognition are frequently intertwined in his study.
In his study, Decoding methods is inextricably linked to Machine learning, which falls within the broad field of Pattern recognition. His research integrates issues of Binary number and Feed forward in his study of Algorithm. His Speech recognition research is multidisciplinary, incorporating elements of Noise measurement, Impulse response, Convolutional neural network and Array processing.
This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.
Non-negative matrix factorization for polyphonic music transcription
P. Smaragdis;J.C. Brown;J.C. Brown.
workshop on applications of signal processing to audio and acoustics (2003)
Blind separation of convolved mixtures in the frequency domain
Convolutive Speech Bases and Their Application to Supervised Speech Separation
IEEE Transactions on Audio, Speech, and Language Processing (2007)
Deep learning for monaural speech separation
Po Sen Huang;Minje Kim;Mark Hasegawa-Johnson;Paris Smaragdis.
international conference on acoustics, speech, and signal processing (2014)
Non-negative matrix factor deconvolution; Extraction of multiple sound sources from monophonic inputs
international conference on independent component analysis and signal separation (2004)
Joint optimization of masks and deep recurrent neural networks for monaural source separation
Po-Sen Huang;Minje Kim;Mark Hasegawa-Johnson;Paris Smaragdis.
IEEE Transactions on Audio, Speech, and Language Processing (2015)
Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
Nasser Mohammadiha;Paris Smaragdis;Arne Leijon.
IEEE Transactions on Audio, Speech, and Language Processing (2013)
Singing-voice separation from monaural recordings using robust principal component analysis
Po-Sen Huang;Scott Deeann Chen;Paris Smaragdis;Mark Hasegawa-Johnson.
international conference on acoustics, speech, and signal processing (2012)
Speech denoising using nonnegative matrix factorization with priors
K.W. Wilson;B. Raj;P. Smaragdis;A. Divakaran.
international conference on acoustics, speech, and signal processing (2008)
Supervised and semi-supervised separation of sounds from single-channel mixtures
Paris Smaragdis;Bhiksha Raj;Madhusudana Shashanka.
international conference on independent component analysis and signal separation (2007)
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: