What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Machine learning
His scientific interests lie mostly in Speech recognition, Artificial intelligence, Artificial neural network, Pattern recognition and Hidden Markov model.
His work on Word error rate as part of general Speech recognition research is often related to Set, thus linking different fields of science.
His work in Artificial intelligence covers topics such as Natural language processing which are related to areas like Context model.
His Artificial neural network research incorporates themes from Singular value decomposition and Feature extraction.
His work in the fields of Speaker recognition and Feature transformation overlaps with other areas such as Merge and Bottleneck.
His Hidden Markov model study incorporates themes from Time delay neural network, Discriminative model and Softmax function.
His most cited work include:
- Recent advances in deep learning for speech research at Microsoft (533 citations)
- Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers (437 citations)
- Restructuring of Deep Neural Network Acoustic Models with Singular Value Decomposition (345 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Word error rate, Artificial neural network and Pattern recognition.
His specific area of interest is Speech recognition, where Yifan Gong studies Acoustic model.
His Artificial intelligence research includes elements of Machine learning and Natural language processing.
His research integrates issues of Language model, Training set, Algorithm, Decoding methods and Robustness in his study of Word error rate.
His research investigates the connection between Artificial neural network and topics such as Dictation that intersect with issues in Regularization and Voice search.
His Pattern recognition research incorporates elements of Speech enhancement, Normalization and Utterance.
He most often published in these fields:
- Speech recognition (82.16%)
- Artificial intelligence (38.50%)
- Word error rate (31.92%)
What were the highlights of his more recent work (between 2019-2021)?
- Speech recognition (82.16%)
- Recurrent neural network (14.55%)
- Word error rate (31.92%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Speech recognition, Recurrent neural network, Word error rate, End-to-end principle and Reduction.
His biological study spans a wide range of topics, including Artificial neural network and Decoding methods.
His research investigates the connection between Artificial neural network and topics such as Embedding that intersect with problems in Attention network.
His Word error rate study combines topics in areas such as Language model, Normalization and Task.
His Training set research entails a greater understanding of Artificial intelligence.
His work on Invariant feature extraction is typically connected to A domain as part of general Artificial intelligence study, connecting several disciplines of science.
Between 2019 and 2021, his most popular works were:
- Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR (22 citations)
- Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability. (20 citations)
- Exploring Pre-Training with Alignments for RNN Transducer Based End-to-End Speech Recognition (18 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Yifan Gong mainly investigates Speech recognition, Recurrent neural network, Word error rate, Initialization and Training set.
Yifan Gong frequently studies issues relating to Reduction and Speech recognition.
His work in Recurrent neural network addresses issues such as End-to-end principle, which are connected to fields such as Heuristic.
In his research on the topic of Word error rate, Interpolation, Connectionism, Task and Leverage is strongly related with Language model.
His Speaker recognition study combines topics from a wide range of disciplines, such as Data set, Robustness and Monaural.
His Speech synthesis research is multidisciplinary, incorporating perspectives in Transducer, Keyword spotting and Speaker adaptation.
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.
