What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Mark D. Plumbley mostly deals with Artificial intelligence, Speech recognition, Pattern recognition, Source separation and Audio signal processing.
The Artificial intelligence study which covers Machine learning that intersects with Feature extraction.
Mark D. Plumbley has included themes like Computational complexity theory, Probabilistic logic, Background noise and Musical in his Speech recognition study.
His Pattern recognition study incorporates themes from Representation and Spectrogram.
His Source separation research is multidisciplinary, incorporating elements of Blind signal separation, Independent component analysis, Signal processing, Principal component analysis and Robustness.
The Audio signal processing study combines topics in areas such as Beat detection, MIDI and Beat.
His most cited work include:
- Best Practices for Scientific Computing (380 citations)
- Detection and Classification of Acoustic Scenes and Events (294 citations)
- Algorithms for nonnegative independent component analysis (213 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Speech recognition, Pattern recognition, Source separation and Artificial neural network.
His Artificial intelligence research includes themes of Machine learning and Non-negative matrix factorization.
The concepts of his Speech recognition study are interwoven with issues in Audio signal processing, Audio signal and Musical.
His studies deal with areas such as Recurrent neural network, Event, Sparse matrix, Task and Signal processing as well as Pattern recognition.
His Source separation research includes elements of Independent component analysis, Distortion, Blind signal separation and Deep neural networks.
He does research in Sparse approximation, focusing on K-SVD specifically.
He most often published in these fields:
- Artificial intelligence (45.68%)
- Speech recognition (37.84%)
- Pattern recognition (29.73%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (45.68%)
- Pattern recognition (29.73%)
- Speech recognition (37.84%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Pattern recognition, Speech recognition, Convolutional neural network and Artificial neural network.
His Pattern recognition research integrates issues from Event, Sound recording and reproduction, Sound and Joint.
His Speech recognition research is multidisciplinary, relying on both Salient and Noise reduction.
His research in Convolutional neural network intersects with topics in Baseline, Receptive field, Pooling, Spectrogram and Audio signal.
Mark D. Plumbley interconnects Feature, F1 score, Offset, Source code and Ground truth in the investigation of issues within Artificial neural network.
His Source separation research entails a greater understanding of Algorithm.
Between 2016 and 2021, his most popular works were:
- Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge (132 citations)
- Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network (107 citations)
- Computational Analysis of Sound Scenes and Events (64 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Mark D. Plumbley focuses on Speech recognition, Artificial intelligence, Pattern recognition, Artificial neural network and Convolutional neural network.
His Word error rate and Source separation study, which is part of a larger body of work in Speech recognition, is frequently linked to Set, bridging the gap between disciplines.
Deep learning, Pattern recognition and Feature are the subjects of his Artificial intelligence studies.
His Pattern recognition research is multidisciplinary, incorporating perspectives in Event, Sound recording and reproduction and Direction of arrival.
His work deals with themes such as Feature extraction, F1 score, Offset and Source code, which intersect with Artificial neural network.
His Convolutional neural network study integrates concerns from other disciplines, such as Recurrent neural network, Sound event detection, Receptive field, Pooling and Spectrogram.
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.
