What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Speech recognition
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Algorithm.
Shigeki Sagayama works in the field of Speech recognition, namely Spectrogram.
He has included themes like Current, Machine learning and Natural language processing in his Artificial intelligence study.
His Hidden Markov model research incorporates themes from Context, Training set, Kanji, Word recognition and Handwriting recognition.
Shigeki Sagayama combines subjects such as Estimation theory and Adaptation with his study of Pattern recognition.
The Algorithm study combines topics in areas such as Noise pollution, Value noise, Jacobian matrix and determinant and Gradient noise.
His most cited work include:
- Dynamic Time-Alignment Kernel in Support Vector Machine (172 citations)
- A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering (147 citations)
- Complex NMF: A new sparse representation for acoustic signals (127 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Algorithm.
His Speech recognition study frequently draws connections to other fields, such as Cluster analysis.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Expectation–maximization algorithm and Natural language processing.
In his research on the topic of Hidden Markov model, Polyphony is strongly related with MIDI.
In the subject of general Pattern recognition, his work in Training set is often linked to Non-negative matrix factorization, thereby combining diverse domains of study.
Shigeki Sagayama focuses mostly in the field of Spectrogram, narrowing it down to topics relating to Acoustics and, in certain cases, Microphone.
He most often published in these fields:
- Speech recognition (63.51%)
- Artificial intelligence (41.95%)
- Hidden Markov model (33.62%)
What were the highlights of his more recent work (between 2011-2020)?
- Speech recognition (63.51%)
- Hidden Markov model (33.62%)
- Artificial intelligence (41.95%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Speech recognition, Hidden Markov model, Artificial intelligence, Pattern recognition and Piano.
His work in Speech recognition addresses subjects such as Transcription, which are connected to disciplines such as Polyrhythm.
His Hidden Markov model research integrates issues from Algorithm, Guitar, Score following and MIDI.
His Artificial intelligence research incorporates elements of Estimation theory, Machine learning, Stochastic modelling and Natural language processing.
His Pattern recognition study incorporates themes from White noise, CMA-ES, Estimation of covariance matrices and Blind signal separation.
His Piano course of study focuses on Jazz and Concatenation.
Between 2011 and 2020, his most popular works were:
- Introduction to the Special Section on Deep Learning for Speech and Language Processing (53 citations)
- Singing Voice Enhancement in Monaural Music Signals Based on Two-stage Harmonic/Percussive Sound Separation on Multiple Resolution Spectrograms (36 citations)
- Dynamic Bayesian Networks for Symbolic Polyphonic Pitch Modeling (35 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Shigeki Sagayama focuses on Speech recognition, Hidden Markov model, Artificial intelligence, Pattern recognition and Spectrogram.
His Viterbi algorithm study in the realm of Speech recognition interacts with subjects such as Input/output.
His studies in Hidden Markov model integrate themes in fields like Machine learning, MIDI, Selection and Rhythm.
His Artificial intelligence study combines topics in areas such as Search engine, Thesaurus, Autoregressive model and Natural language processing.
His Feature vector study in the realm of Pattern recognition connects with subjects such as Matrix decomposition, Non-negative matrix factorization and Hidden markov models speech recognition.
His research integrates issues of Source separation and Harmonic in his study of Spectrogram.
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.
