What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Speech recognition
Artificial intelligence, Speech recognition, Natural language processing, Mandarin Chinese and Vocabulary are his primary areas of study.
He has researched Artificial intelligence in several fields, including Adaptation and Pattern recognition.
His Speech recognition research is multidisciplinary, relying on both Sentence, Unsupervised learning, Autoencoder and Word.
His Natural language processing research includes elements of Search engine indexing and Speech synthesis.
His work deals with themes such as Dictation, Chinese characters, Chinese language, Character and Syllable, which intersect with Mandarin Chinese.
His research investigates the connection with Vocabulary and areas like Syllabic verse which intersect with concerns in Mandarin speech recognition.
His most cited work include:
- A DISTRIBUTED ARCHITECTURE FOR COOPERATIVE SPOKEN DIALOGUE AGENTS WITH COHERENT DIALOGUE STATE AND HISTORY (237 citations)
- A real-time Mandarin dictation machine for Chinese language with unlimited texts and very large vocabulary (175 citations)
- A new framework for recognition of Mandarin syllables with tones using sub-syllabic units (174 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Speech recognition, Natural language processing, Mandarin Chinese and Pattern recognition.
His Artificial intelligence study typically links adjacent topics like Chinese language.
His Speech recognition research focuses on Vocabulary and how it relates to Speech corpus.
His work carried out in the field of Natural language processing brings together such families of science as Document retrieval and Information retrieval.
His studies deal with areas such as Structure and Key as well as Information retrieval.
His Mandarin Chinese research integrates issues from Dictation, Chinese characters, Speech synthesis, Character and Tone.
He most often published in these fields:
- Artificial intelligence (65.88%)
- Speech recognition (62.56%)
- Natural language processing (47.39%)
What were the highlights of his more recent work (between 2012-2021)?
- Speech recognition (62.56%)
- Artificial intelligence (65.88%)
- Natural language processing (47.39%)
In recent papers he was focusing on the following fields of study:
Lin-Shan Lee spends much of his time researching Speech recognition, Artificial intelligence, Natural language processing, Term and Hidden Markov model.
His Speech recognition study combines topics in areas such as Artificial neural network, Autoencoder and Feature.
Artificial intelligence is frequently linked to Pattern recognition in his study.
His Natural language processing study integrates concerns from other disciplines, such as Semantics, Recurrent neural network and Word.
His Hidden Markov model research incorporates themes from Transcription and Mandarin Chinese.
His research in Mandarin Chinese intersects with topics in Consistency and Space.
Between 2012 and 2021, his most popular works were:
- Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoder. (103 citations)
- Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations (78 citations)
- Spoken content retrieval: beyond cascading speech recognition with text retrieval (71 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Lin-Shan Lee mostly deals with Artificial intelligence, Speech recognition, Natural language processing, Language model and Autoencoder.
His biological study spans a wide range of topics, including Key and Pattern recognition.
The various areas that he examines in his Speech recognition study include Encoder, Cluster analysis, Feature vector, Decoding methods and Unsupervised learning.
His biological study spans a wide range of topics, including Pronunciation, Recurrent neural network, First language, Query expansion and Markov decision process.
In his study, Vocabulary, Lexicon, Computational linguistics and Mandarin Chinese is inextricably linked to Spoken language, which falls within the broad field of Language model.
His research in Autoencoder intersects with topics in Segmentation, Representation, Utterance and Word2vec.
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.
