What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Statistics
His main research concerns Speech recognition, Artificial intelligence, Speech processing, Natural language processing and Hidden Markov model.
His research integrates issues of Artificial neural network, Vocabulary and Microphone in his study of Speech recognition.
His Artificial intelligence research incorporates themes from Loudspeaker and Pattern recognition.
The study incorporates disciplines such as Acoustics and Speech enhancement in addition to Speech processing.
His Hidden Markov model research integrates issues from Markov model and Maximum-entropy Markov model.
His work deals with themes such as Backpropagation and Task, which intersect with Time delay neural network.
His most cited work include:
- Phoneme recognition using time-delay neural networks (2088 citations)
- Julius --- An Open Source Real-Time Large Vocabulary Recognition Engine (437 citations)
- Voice conversion through vector quantization (401 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Pattern recognition, Blind signal separation and Hidden Markov model.
Kiyohiro Shikano specializes in Speech recognition, namely Speech processing.
His Artificial intelligence research integrates issues from Vocabulary and Natural language processing.
The concepts of his Pattern recognition study are interwoven with issues in Signal and Separation.
His studies in Blind signal separation integrate themes in fields like Independent component analysis, Algorithm, Source separation, Frequency domain and Monaural.
Kiyohiro Shikano has included themes like Artificial neural network, Speaker recognition, Sufficient statistic and Speaker adaptation in his Hidden Markov model study.
He most often published in these fields:
- Speech recognition (77.16%)
- Artificial intelligence (34.44%)
- Pattern recognition (18.78%)
What were the highlights of his more recent work (between 2007-2015)?
- Speech recognition (77.16%)
- Artificial intelligence (34.44%)
- Speech enhancement (8.47%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Speech recognition, Artificial intelligence, Speech enhancement, Noise and Blind signal separation.
His study in Speech recognition is interdisciplinary in nature, drawing from both Higher-order statistics, Noise measurement and Microphone.
His Artificial intelligence research incorporates elements of Natural language processing, Many-to-many and Pattern recognition.
His research in Pattern recognition intersects with topics in Kernel and Kurtosis.
His study on Noise also encompasses disciplines like
- Noise reduction that intertwine with fields like Minimum mean square error,
- Algorithm which intersects with area such as Beamforming.
His Blind signal separation research is multidisciplinary, incorporating perspectives in Independent component analysis, Frequency domain, Noise and Source separation.
Between 2007 and 2015, his most popular works were:
- Statistical Voice Conversion Techniques for Body-Conducted Unvoiced Speech Enhancement (124 citations)
- Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech (112 citations)
- Blind Spatial Subtraction Array for Speech Enhancement in Noisy Environment (97 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Speech recognition
- Statistics
His primary areas of study are Speech recognition, Speech enhancement, Speech processing, Artificial intelligence and Microphone.
Kiyohiro Shikano works on Speech recognition which deals in particular with Voice activity detection.
The various areas that he examines in his Speech processing study include Intelligibility, Speaker recognition and Audio signal.
His Artificial intelligence study integrates concerns from other disciplines, such as Natural language processing, Nonlinear circuits, Many-to-many, Maximum likelihood and Pattern recognition.
His Microphone research is multidisciplinary, relying on both Acoustic model, Audio mining, Impulse response and Reverberation.
His Impulse response study which covers Robustness that intersects with Hidden Markov model.
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.
