What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Machine learning
The scientist’s investigation covers issues in Artificial intelligence, Speech recognition, Artificial neural network, Pattern recognition and Hidden Markov model.
His Artificial intelligence study integrates concerns from other disciplines, such as Machine learning and Natural language processing.
His Speech recognition research is multidisciplinary, relying on both Mixture model, Discriminative model and Deep neural networks.
His Artificial neural network research includes themes of Set, Layer and Convolutional neural network.
His biological study spans a wide range of topics, including Computational auditory scene analysis and Cluster analysis.
His studies in Hidden Markov model integrate themes in fields like Gradient descent, Regularization, Speaker recognition and Softmax function.
His most cited work include:
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups (6052 citations)
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition (2360 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?
Dong Yu mainly focuses on Speech recognition, Artificial intelligence, Artificial neural network, Word error rate and Pattern recognition.
His work carried out in the field of Speech recognition brings together such families of science as Time delay neural network, Recurrent neural network and Discriminative model.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Machine learning and Natural language processing.
His Word error rate research is multidisciplinary, relying on both Noise, Utterance, Reduction and TIMIT.
His Pattern recognition study integrates concerns from other disciplines, such as Estimation theory, Feature, Layer and Deep neural networks.
He has included themes like Mixture model, Speech processing and Conditional random field in his Hidden Markov model study.
He most often published in these fields:
- Speech recognition (65.10%)
- Artificial intelligence (48.51%)
- Artificial neural network (26.49%)
What were the highlights of his more recent work (between 2019-2021)?
- Speech recognition (65.10%)
- Artificial intelligence (48.51%)
- Artificial neural network (26.49%)
In recent papers he was focusing on the following fields of study:
Dong Yu focuses on Speech recognition, Artificial intelligence, Artificial neural network, Word error rate and Deep learning.
His Speech recognition research incorporates elements of Embedding, Beamforming, Speech enhancement, Discriminative model and Joint.
His Artificial intelligence study frequently involves adjacent topics like Natural language processing.
The various areas that Dong Yu examines in his Artificial neural network study include Language model, Training set, Leverage, NIST and Transfer of learning.
His studies deal with areas such as Modality and Reverberation as well as Word error rate.
His Deep learning study incorporates themes from Spatial filter and Pattern recognition.
Between 2019 and 2021, his most popular works were:
- Multi-Modal Multi-Channel Target Speech Separation (15 citations)
- MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning (12 citations)
- Enhancing End-to-End Multi-Channel Speech Separation Via Spatial Feature Learning (12 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Speech recognition, Artificial intelligence, Artificial neural network, End-to-end principle and Deep learning.
Many of his research projects under Speech recognition are closely connected to Separation with Separation, tying the diverse disciplines of science together.
His biological study spans a wide range of topics, including Paragraph, Coreference and Natural language processing.
Within one scientific family, he focuses on topics pertaining to Training set under Artificial neural network, and may sometimes address concerns connected to Keyword spotting, Speech training, Transfer of learning and NIST.
Dong Yu interconnects Layer, SIGNAL, Spatial filter, Speech synthesis and Convolution in the investigation of issues within End-to-end principle.
He combines subjects such as Flexibility, Kernel, Audio visual and Pattern recognition with his study of Deep learning.
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.
