What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Linguistics
- Programming language
Artificial intelligence, Natural language processing, Speech recognition, Linguistics and Word are his primary areas of study.
Richard Sproat has researched Artificial intelligence in several fields, including Pronunciation, Intonation and Index.
His research in Natural language processing is mostly concerned with Natural language.
His Natural language research is multidisciplinary, incorporating perspectives in Programming language, Software, Compiler and Interface.
His work carried out in the field of Speech recognition brings together such families of science as Segmentation, Named entity, Search engine indexing and Transliteration.
Many of his studies involve connections with topics such as Cognitive science and Linguistics.
His most cited work include:
- Emotions from Text: Machine Learning for Text-based Emotion Prediction (580 citations)
- Allophonic variation in English /l/ and its implications for phonetic implementation (369 citations)
- WordsEye: an automatic text-to-scene conversion system (341 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Natural language processing, Linguistics, Speech recognition and Speech synthesis.
His Artificial intelligence research incorporates themes from Pronunciation and Set.
His Set study combines topics in areas such as Polysemy and Representation.
His Natural language processing research integrates issues from Text to speech synthesis and Grammar.
His work on Linguistics deals in particular with Phonology, Mandarin Chinese, Symbol, Syllable and Morpheme.
His Speech recognition study integrates concerns from other disciplines, such as Named entity and Hindi.
He most often published in these fields:
- Artificial intelligence (49.50%)
- Natural language processing (44.00%)
- Linguistics (27.50%)
What were the highlights of his more recent work (between 2013-2021)?
- Artificial intelligence (49.50%)
- Natural language processing (44.00%)
- Text normalization (10.00%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Natural language processing, Text normalization, Speech recognition and Linguistics.
The concepts of his Artificial intelligence study are interwoven with issues in Simple and Estimator.
He performs multidisciplinary study in Natural language processing and Task in his work.
His Text normalization research includes elements of Parsing, Encoder, Bengali and Semiotics.
His Speech recognition research integrates issues from Principle of maximum entropy and Spoken language processing.
The various areas that Richard Sproat examines in his Linguistics study include Word list and Set.
Between 2013 and 2021, his most popular works were:
- RNN Approaches to Text Normalization: A Challenge. (56 citations)
- The Kestrel TTS text normalization system (33 citations)
- Neural models of text normalization for speech applications (29 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Linguistics
- Programming language
Richard Sproat focuses on Speech recognition, Text normalization, Artificial intelligence, Natural language processing and Normalization.
The study incorporates disciplines such as Artificial neural network, Recurrent neural network and Domain in addition to Speech recognition.
His work carried out in the field of Recurrent neural network brings together such families of science as Crowdsourcing, Hindi, Bengali and Leverage.
His Text normalization research is multidisciplinary, incorporating elements of Component, Protocol, Rule-based machine translation and Code.
His Principle of maximum entropy research extends to Natural language processing, which is thematically connected.
His research investigates the connection between Normalization and topics such as Machine learning that intersect with issues in Training 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.
