What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer network
- Programming language
The scientist’s investigation covers issues in Artificial intelligence, Object detection, Pyramid, Computer security and Network architecture.
His Artificial intelligence research integrates issues from Mobile device and Computer engineering.
His Computer engineering research is multidisciplinary, incorporating elements of Latency, Code, Tree, Deep learning and Task.
Borrowing concepts from Mobile phone, he weaves in ideas under Pyramid.
The Packet trace research he does as part of his general Computer security study is frequently linked to other disciplines of science, such as Process, TRACE and Permission, therefore creating a link between diverse domains of science.
His work deals with themes such as Network planning and design, Segmentation, Pattern recognition, Pooling and Search algorithm, which intersect with Network architecture.
His most cited work include:
- MnasNet: Platform-Aware Neural Architecture Search for Mobile (873 citations)
- Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions (777 citations)
- Searching for MobileNetV3 (506 citations)
What are the main themes of his work throughout his whole career to date?
Ruoming Pang spends much of his time researching Speech recognition, Word error rate, End-to-end principle, Recurrent neural network and Encoder.
His Speech recognition research is multidisciplinary, relying on both Artificial neural network, Word, Reduction and Test set.
His work carried out in the field of Word error rate brings together such families of science as Beam search, Latency and Inference.
His Recurrent neural network research incorporates themes from Leverage and Transformer.
His Convolutional neural network study also includes
- Task which is related to area like Code and Object detection,
- Computer engineering, which have a strong connection to Pyramid.
The Object detection study which covers Pattern recognition that intersects with Artificial intelligence.
He most often published in these fields:
- Speech recognition (56.18%)
- Word error rate (21.35%)
- End-to-end principle (20.22%)
What were the highlights of his more recent work (between 2020-2021)?
- Speech recognition (56.18%)
- Word error rate (21.35%)
- Word (10.11%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Speech recognition, Word error rate, Word, Latency and Reduction.
The concepts of his Speech recognition study are interwoven with issues in Data modeling and Recurrent neural network.
His biological study spans a wide range of topics, including Latency, Baseline, Learning methods, Data set and Test set.
His studies in Latency integrate themes in fields like Convolution, Labeled data, Hardware architecture and FLOPS.
Ruoming Pang has researched Reduction in several fields, including Computer engineering and Transformer.
His Transformer research is multidisciplinary, incorporating perspectives in Layer, Decoding methods and Encoding.
Between 2020 and 2021, his most popular works were:
- Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling (4 citations)
- FastEmit: Low-Latency Streaming ASR with Sequence-Level Emission Regularization (3 citations)
- Searching for Fast Model Families on Datacenter Accelerators. (3 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer network
- Programming language
Latency, Word error rate, Latency, Word and Speech recognition are his primary areas of study.
The Latency study combines topics in areas such as Joint and FLOPS.
His Word error rate research includes elements of Beam search, Algorithm, End-to-end principle and Degradation.
His study in Latency is interdisciplinary in nature, drawing from both Regularization, Latency, Reduction, Voice search and Test set.
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.
