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, Hidden Markov model, Pattern recognition and Vocabulary.
His Speech recognition study frequently intersects with other fields, such as Robustness.
His work carried out in the field of Artificial intelligence brings together such families of science as Estimation theory, Machine learning and Natural language processing.
He combines subjects such as Speech synthesis, Parametric statistics and Markov model with his study of Hidden Markov model.
His research integrates issues of Maximum likelihood, Covariance and Noisy data in his study of Pattern recognition.
His Vocabulary study combines topics from a wide range of disciplines, such as Transcription, Discriminative model, Recognition system and Cluster analysis.
His most cited work include:
- Maximum likelihood linear transformations for HMM-based speech recognition (1440 citations)
- Semi-tied covariance matrices for hidden Markov models (533 citations)
- Application of Hidden Markov Models in Speech Recognition (480 citations)
What are the main themes of his work throughout his whole career to date?
Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Natural language processing are his primary areas of study.
Mark J. F. Gales works mostly in the field of Speech recognition, limiting it down to topics relating to Vocabulary and, in certain cases, Transcription.
His Artificial intelligence research focuses on subjects like Machine learning, which are linked to Training set, Decoding methods and Estimation theory.
The study incorporates disciplines such as Markov model and Robustness in addition to Hidden Markov model.
His work on Support vector machine, Feature vector, Mixture model and Feature extraction as part of his general Pattern recognition study is frequently connected to Adaptation, thereby bridging the divide between different branches of science.
His Natural language processing study integrates concerns from other disciplines, such as Pronunciation, Context and Word.
He most often published in these fields:
- Speech recognition (71.63%)
- Artificial intelligence (62.92%)
- Hidden Markov model (23.60%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (62.92%)
- Speech recognition (71.63%)
- Machine learning (19.10%)
In recent papers he was focusing on the following fields of study:
Mark J. F. Gales mainly investigates Artificial intelligence, Speech recognition, Machine learning, Natural language processing and Spoken language.
His study brings together the fields of Pronunciation and Artificial intelligence.
The Pronunciation study which covers Phone that intersects with Vocabulary.
His studies deal with areas such as Transcription and Recurrent neural network as well as Speech recognition.
In his study, which falls under the umbrella issue of Machine learning, Inference is strongly linked to Machine translation.
He has researched Spoken language in several fields, including Spontaneous speech, Language assessment and First language.
Between 2016 and 2021, his most popular works were:
- Predictive uncertainty estimation via prior networks (156 citations)
- Predictive Uncertainty Estimation via Prior Networks (51 citations)
- Ensemble Distribution Distillation (30 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His scientific interests lie mostly in Artificial intelligence, Speech recognition, Machine learning, Artificial neural network and Training set.
His research on Artificial intelligence often connects related topics like Natural language processing.
Language model and Hidden Markov model are the subjects of his Speech recognition studies.
His Hidden Markov model research includes themes of Ensemble learning, Decoding methods and First language.
His Artificial neural network study combines topics in areas such as Class, Algorithm and Task.
His Transcription research incorporates elements of Feature extraction, Vocabulary and Phone.
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.
