What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
His primary areas of study are Artificial intelligence, Speech recognition, Pattern recognition, Feature extraction and Artificial neural network.
His research in Artificial intelligence intersects with topics in Frame and Computer vision.
Eng Siong Chng focuses mostly in the field of Speech recognition, narrowing it down to matters related to Natural language processing and, in some cases, Vocabulary.
His work on Dimensionality reduction as part of general Pattern recognition study is frequently linked to Linear combination, bridging the gap between disciplines.
His research in Feature extraction tackles topics such as Hidden Markov model which are related to areas like Rule-based system.
His Artificial neural network research includes elements of Subspace topology, Algorithm and Robustness.
His most cited work include:
- Regularized orthogonal least squares algorithm for constructing radial basis function networks (205 citations)
- A learning-based approach to direction of arrival estimation in noisy and reverberant environments (169 citations)
- Gradient radial basis function networks for nonlinear and nonstationary time series prediction (133 citations)
What are the main themes of his work throughout his whole career to date?
Eng Siong Chng mainly focuses on Speech recognition, Artificial intelligence, Pattern recognition, Natural language processing and Word error rate.
His Mixture model research extends to the thematically linked field of Speech recognition.
His Artificial intelligence study often links to related topics such as NIST.
His Pattern recognition research is multidisciplinary, relying on both Normalization, Feature, Robustness and Spectrogram.
His Natural language processing research incorporates themes from Context, Vocabulary and Phone.
He has included themes like Word, Reduction, Code-switching and Lexicon in his Language model study.
He most often published in these fields:
- Speech recognition (63.30%)
- Artificial intelligence (53.18%)
- Pattern recognition (25.47%)
What were the highlights of his more recent work (between 2018-2021)?
- Speech recognition (63.30%)
- Embedding (5.62%)
- Word error rate (15.73%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Speech recognition, Embedding, Word error rate, Language model and Signal.
His Speech recognition research is multidisciplinary, incorporating elements of Time domain, PESQ, End-to-end principle, Encoder and Code-switching.
His work deals with themes such as Data modeling, Boosting, Reduction and Transformer, which intersect with Word error rate.
In his study, which falls under the umbrella issue of Signal, Phone, Language identification and Vocabulary is strongly linked to Utterance.
His WordNet study is related to the wider topic of Artificial intelligence.
The various areas that Eng Siong Chng examines in his Artificial intelligence study include Noise measurement and Readability.
Between 2018 and 2021, his most popular works were:
- On the End-to-End Solution to Mandarin-English Code-Switching Speech Recognition. (27 citations)
- Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss (19 citations)
- Time-Domain Speaker Extraction Network (15 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Eng Siong Chng mainly investigates Speech recognition, Embedding, Signal, Encoder and Time domain.
The concepts of his Speech recognition study are interwoven with issues in PESQ, Word and Code-switching.
His PESQ research also works with subjects such as
- Signal reconstruction which intersects with area such as Sound recording and reproduction, Source separation, Artificial neural network, Context and Phase,
- Frequency domain that intertwine with fields like Cocktail party effect, Speech processing, Decoding methods and Feature extraction.
His Code-switching study combines topics in areas such as End-to-end principle, Utterance and Vocabulary.
His Encoder research includes themes of Window, Pipeline and Speech coding.
His Speaker verification study integrates concerns from other disciplines, such as Reduction and Speaker diarisation.
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.
