What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
His primary areas of investigation include Artificial intelligence, Speech recognition, Pattern recognition, Blind signal separation and Artificial neural network.
His Artificial intelligence study frequently draws parallels with other fields, such as Direction of arrival.
The study incorporates disciplines such as Artifact, Noise reduction, Constraint and Signal processing in addition to Speech recognition.
Wenwu Wang combines subjects such as Feature and Spectrogram with his study of Pattern recognition.
His Blind signal separation study also includes
- Source separation, which have a strong connection to Frequency domain and Speech processing,
- Microphone which connect with Robustness.
His work carried out in the field of Artificial neural network brings together such families of science as Deep learning, Feature learning and Word error rate.
His most cited work include:
- Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network (107 citations)
- Penalty function-based joint diagonalization approach for convolutive blind separation of nonstationary sources (79 citations)
- Simultaneous Codeword Optimization (SimCO) for Dictionary Update and Learning (62 citations)
What are the main themes of his work throughout his whole career to date?
Wenwu Wang focuses on Artificial intelligence, Speech recognition, Pattern recognition, Algorithm and Source separation.
His research in Artificial intelligence intersects with topics in Machine learning and Computer vision.
His studies deal with areas such as Artificial neural network, Reverberation and Blind signal separation as well as Speech recognition.
The Blind signal separation study combines topics in areas such as Underdetermined system, Independent component analysis, Frequency domain and Signal processing.
His Pattern recognition study frequently draws connections between related disciplines such as Cluster analysis.
His Algorithm research integrates issues from Function, Matrix decomposition, Non-negative matrix factorization and Mathematical optimization.
He most often published in these fields:
- Artificial intelligence (51.48%)
- Speech recognition (38.69%)
- Pattern recognition (35.74%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (51.48%)
- Pattern recognition (35.74%)
- Convolutional neural network (12.13%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Pattern recognition, Convolutional neural network, Speech recognition and Algorithm.
His Artificial intelligence study incorporates themes from Machine learning and Sound recording and reproduction.
His Pattern recognition study combines topics in areas such as Representation, Transformer, Joint and Task.
His Convolutional neural network research is multidisciplinary, incorporating elements of Recurrent neural network, Sound event detection, Discriminative model and Spectrogram.
His research on Speech recognition often connects related areas such as Artificial neural network.
The various areas that Wenwu Wang examines in his Algorithm study include Noise, Gradient descent, Neural coding, Function and Noise measurement.
Between 2017 and 2021, his most popular works were:
- Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network (107 citations)
- Audio Set Classification with Attention Model: A Probabilistic Perspective (61 citations)
- Sound Event Detection and Time–Frequency Segmentation from Weakly Labelled Data (50 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Wenwu Wang spends much of his time researching Artificial neural network, Pattern recognition, Artificial intelligence, Convolutional neural network and Speech recognition.
His work deals with themes such as Feature extraction, Direction of arrival, Joint and Noise, which intersect with Artificial neural network.
His Pattern recognition research incorporates elements of Sound recording and reproduction, Representation and Overfitting.
His studies in Artificial intelligence integrate themes in fields like Phase retrieval and Least squares.
His Convolutional neural network study combines topics from a wide range of disciplines, such as Feature, F1 score, Sound event detection and Spectrogram.
The Speech recognition study which covers Class that intersects with Salient, Perspective and Probability measure.
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.
