What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Programming language
The scientist’s investigation covers issues in Speech recognition, Artificial neural network, Artificial intelligence, Time delay neural network and Hidden Markov model.
His Speech recognition research includes elements of Mixture model, Convolutional neural network, Pattern recognition and Deep learning.
Abdel-rahman Mohamed works mostly in the field of Mixture model, limiting it down to topics relating to Margin and, in certain cases, State, as a part of the same area of interest.
His work on Feature extraction as part of general Pattern recognition study is frequently linked to Generative model, therefore connecting diverse disciplines of science.
His research ties Acoustic model and Time delay neural network together.
His TIMIT research incorporates themes from Recurrent neural network, Machine learning and Word error rate.
His most cited work include:
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups (6052 citations)
- Speech recognition with deep recurrent neural networks (5020 citations)
- Deep Neural Networks for Acoustic Modeling in Speech Recognition (1745 citations)
What are the main themes of his work throughout his whole career to date?
Abdel-rahman Mohamed focuses on Artificial intelligence, Speech recognition, Artificial neural network, Pattern recognition and Machine learning.
His research on Artificial intelligence frequently links to adjacent areas such as Natural language processing.
His Speech recognition research is multidisciplinary, relying on both Time delay neural network, Recurrent neural network and Convolutional neural network.
His research integrates issues of Acoustic model, Test set, Phrase and Benchmark in his study of Recurrent neural network.
His biological study spans a wide range of topics, including Program synthesis, Set, Hidden Markov model and Spectrogram.
His work in Hidden Markov model tackles topics such as Mixture model which are related to areas like Feature vector.
He most often published in these fields:
- Artificial intelligence (54.93%)
- Speech recognition (54.93%)
- Artificial neural network (35.21%)
What were the highlights of his more recent work (between 2019-2021)?
- Speech recognition (54.93%)
- Feature learning (8.45%)
- Artificial intelligence (54.93%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Speech recognition, Feature learning, Artificial intelligence, Reduction and Semi-supervised learning.
His Speech recognition research includes themes of Embedding, Transformer and Machine translation.
He has researched Transformer in several fields, including Language model, Artificial neural network, Recurrent neural network and Training set.
His Feature learning research is multidisciplinary, incorporating perspectives in Speech processing and Benchmark.
His Speech processing study combines topics from a wide range of disciplines, such as Word error rate, Machine learning, Deep learning, Adaptation and Cross lingual.
His research on Artificial intelligence focuses in particular on Representation.
Between 2019 and 2021, his most popular works were:
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (126 citations)
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (97 citations)
- Transformer-Based Acoustic Modeling for Hybrid Speech Recognition (64 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
His primary scientific interests are in Speech recognition, Natural language processing, Artificial intelligence, Self supervised learning and Artificial neural network.
His research in Speech recognition intersects with topics in Scheme, Automatic summarization and Machine translation.
Particularly relevant to Recurrent neural network is his body of work in Artificial neural network.
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.
