What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
His primary scientific interests are in Speech recognition, Artificial intelligence, Hidden Markov model, Word and Markov model.
Stephen E. Levinson has researched Speech recognition in several fields, including Vector quantization and Cluster analysis.
His work deals with themes such as Natural language processing, Vocabulary and Pattern recognition, which intersect with Artificial intelligence.
His Pattern recognition course of study focuses on Word error rate and Maximum-entropy Markov model.
The concepts of his Hidden Markov model study are interwoven with issues in Affective computing, Feature extraction, Facial expression and Feature selection.
Stephen E. Levinson studied Word and Dynamic time warping that intersect with Pattern recognition.
His most cited work include:
- An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition (919 citations)
- Continuously variable duration hidden Markov models for automatic speech recognition (428 citations)
- Considerations in dynamic time warping algorithms for discrete word recognition (322 citations)
What are the main themes of his work throughout his whole career to date?
Stephen E. Levinson mainly focuses on Speech recognition, Artificial intelligence, Natural language processing, Vocabulary and Hidden Markov model.
His work carried out in the field of Speech recognition brings together such families of science as Word and Parsing.
His research integrates issues of Computer vision and Pattern recognition in his study of Artificial intelligence.
Stephen E. Levinson combines subjects such as Sentence, Grammar and Lexicon with his study of Vocabulary.
His Hidden Markov model research is multidisciplinary, incorporating elements of Vector quantization, State, Markov model and Phonetic form.
His study in the field of Hidden semi-Markov model also crosses realms of Gaussian.
He most often published in these fields:
- Speech recognition (60.12%)
- Artificial intelligence (60.12%)
- Natural language processing (28.32%)
What were the highlights of his more recent work (between 2002-2017)?
- Artificial intelligence (60.12%)
- Speech recognition (60.12%)
- Natural language processing (28.32%)
In recent papers he was focusing on the following fields of study:
Stephen E. Levinson focuses on Artificial intelligence, Speech recognition, Natural language processing, Hidden Markov model and Robot.
His Artificial intelligence study integrates concerns from other disciplines, such as Computer vision and Pattern recognition.
His biological study spans a wide range of topics, including Principle of maximum entropy, Synthetic data and Markov model.
The Speech recognition study combines topics in areas such as Affective computing, Speech communication and Spoken language.
His studies deal with areas such as Prosody and Intelligent tutoring system as well as Natural language processing.
The Viterbi algorithm research Stephen E. Levinson does as part of his general Hidden Markov model study is frequently linked to other disciplines of science, such as Term, therefore creating a link between diverse domains of science.
Between 2002 and 2017, his most popular works were:
- Audio-Visual Affect Recognition (98 citations)
- Bimodal HCI-related affect recognition (51 citations)
- Audio-visual affect recognition through multi-stream fused HMM for HCI (49 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Stephen E. Levinson spends much of his time researching Artificial intelligence, Speech recognition, Hidden Markov model, Pattern recognition and Natural language.
His Artificial intelligence study frequently links to related topics such as Computer vision.
His study in the field of Emotion recognition is also linked to topics like Affect.
His Hidden Markov model study incorporates themes from Syntax and Mobile robot.
The study incorporates disciplines such as Principle of maximum entropy and Markov model in addition to Pattern recognition.
Stephen E. Levinson interconnects Robot, Reinforcement learning, Parsing and Social robot in the investigation of issues within Natural language.
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.
