What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Statistics
His primary scientific interests are in Speech recognition, Artificial intelligence, Natural language processing, Speaker recognition and Hidden Markov model.
His work is connected to Speech processing, Word error rate, Speech coding, Acoustic model and Cepstrum, as a part of Speech recognition.
His Word error rate research is multidisciplinary, relying on both Word recognition, Feature selection and Linear predictive coding.
His Artificial intelligence research includes elements of Set and Pattern recognition.
His Natural language processing research includes themes of Word, Grammar and Spontaneous speech.
His study in Speaker recognition is interdisciplinary in nature, drawing from both Normalization, Feature and Vocabulary.
His most cited work include:
- Cepstral analysis technique for automatic speaker verification (1097 citations)
- Speaker-independent isolated word recognition using dynamic features of speech spectrum (685 citations)
- Digital Speech Processing, Synthesis, and Recognition (398 citations)
What are the main themes of his work throughout his whole career to date?
Sadaoki Furui mainly investigates Speech recognition, Artificial intelligence, Natural language processing, Hidden Markov model and Pattern recognition.
His Speech recognition study is mostly concerned with Speaker recognition, Speech processing, Language model, Word error rate and Acoustic model.
The Word error rate study combines topics in areas such as Transcription and Word recognition.
His Artificial intelligence study frequently draws connections between related disciplines such as Noise.
His work deals with themes such as Vocabulary and Set, which intersect with Natural language processing.
His Hidden Markov model study incorporates themes from Cepstrum, Markov model and Robustness.
He most often published in these fields:
- Speech recognition (74.48%)
- Artificial intelligence (57.57%)
- Natural language processing (34.12%)
What were the highlights of his more recent work (between 2008-2018)?
- Speech recognition (74.48%)
- Artificial intelligence (57.57%)
- Natural language processing (34.12%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Natural language processing, Pattern recognition and Hidden Markov model.
Sadaoki Furui has included themes like Vocabulary and Adaptation in his Speech recognition study.
His research investigates the connection between Artificial intelligence and topics such as Identification that intersect with problems in Variation.
His research in the fields of Language model overlaps with other disciplines such as Character.
His research in Pattern recognition intersects with topics in Robustness and Noise.
Sadaoki Furui interconnects Cross-validation and Word error rate in the investigation of issues within Hidden Markov model.
Between 2008 and 2018, his most popular works were:
- Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition (49 citations)
- Fast acoustic computations using graphics processors (43 citations)
- Automatic Chinese Abbreviation Generation Using Conditional Random Field (23 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Speech recognition
- Statistics
Sadaoki Furui focuses on Speech recognition, Artificial intelligence, Natural language processing, Hidden Markov model and Pattern recognition.
His Speech recognition study combines topics from a wide range of disciplines, such as Variable and Vocabulary.
His Artificial intelligence study integrates concerns from other disciplines, such as Algorithm and Machine learning.
The study incorporates disciplines such as Speech corpus and Information retrieval in addition to Natural language processing.
Sadaoki Furui has researched Hidden Markov model in several fields, including Automatic summarization, Acoustic model and Adaptation.
In his research, Word error rate and Reduction is intimately related to Cross-validation, which falls under the overarching field of Pattern recognition.
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.
