What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Programming language
Xuedong Huang focuses on Speech recognition, Artificial intelligence, Language model, Hidden Markov model and Natural language processing.
His Speech recognition research is multidisciplinary, incorporating perspectives in Context, Process and Set.
His study explores the link between Artificial intelligence and topics such as Pattern recognition that cross with problems in Reduction, Noise reduction and Noise.
His study focuses on the intersection of Language model and fields such as Acoustic model with connections in the field of Recurrent neural network, Test set, NIST and Theoretical computer science.
His studies in Hidden Markov model integrate themes in fields like Hidden semi-Markov model, Markov process, Markov model, Variable-order Markov model and Vocabulary.
His research investigates the link between Speech synthesis and topics such as Speech processing that cross with problems in Spoken language and Audio signal.
His most cited work include:
- Spoken Language Processing: A Guide to Theory, Algorithm, and System Development (1205 citations)
- Hidden Markov Models for Speech Recognition (752 citations)
- Spoken Language Processing (748 citations)
What are the main themes of his work throughout his whole career to date?
Xuedong Huang mainly focuses on Speech recognition, Artificial intelligence, Natural language processing, Hidden Markov model and Word error rate.
Xuedong Huang has researched Speech recognition in several fields, including Word and Microphone.
Much of his study explores Artificial intelligence relationship to Pattern recognition.
His work investigates the relationship between Hidden Markov model and topics such as Codebook that intersect with problems in Vector quantization.
His Speech processing research focuses on Spoken language and how it connects with Human–computer interaction.
His study on Perplexity is often connected to Cache language model as part of broader study in Language model.
He most often published in these fields:
- Speech recognition (47.93%)
- Artificial intelligence (38.43%)
- Natural language processing (22.31%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (38.43%)
- Natural language processing (22.31%)
- Automatic summarization (6.61%)
In recent papers he was focusing on the following fields of study:
Xuedong Huang spends much of his time researching Artificial intelligence, Natural language processing, Automatic summarization, Speech recognition and Language model.
His study in the field of Utterance and Machine translation also crosses realms of Invariant and Parity.
The concepts of his Natural language processing study are interwoven with issues in Graph, Knowledge graph, Identifier, User device and Transcription.
His Automatic summarization research also works with subjects such as
- Transformer that connect with fields like Recurrent neural network, Noise reduction and Effective method,
- Salient that intertwine with fields like Zero, Quality, Benchmark and Shot,
- Decoding methods and Graph computation most often made with reference to Boosting.
His study in Speech recognition is interdisciplinary in nature, drawing from both Microphone and Audio signal.
As part of the same scientific family, he usually focuses on Language model, concentrating on Leverage and intersecting with Labeled data.
Between 2017 and 2021, his most popular works were:
- Achieving Human Parity on Automatic Chinese to English News Translation (304 citations)
- The Microsoft 2017 Conversational Speech Recognition System (228 citations)
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering (72 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Microsoft Windows
Xuedong Huang mostly deals with Artificial intelligence, Natural language processing, Automatic summarization, Speech recognition and Word error rate.
His Artificial intelligence study combines topics in areas such as Contextual design and Conversation.
His work on Language model and Machine translation as part of general Natural language processing research is often related to Parity, thus linking different fields of science.
His Automatic summarization study also includes fields such as
- Transformer that connect with fields like Noise reduction, Recurrent neural network, Salient and Effective method,
- Knowledge graph, which have a strong connection to Boosting, Correctness and Commonsense knowledge.
His Speech recognition research includes elements of Frame, Session and Context model.
The various areas that Xuedong Huang examines in his Word error rate study include Set, NIST, Acoustic model, Dialog box 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.
