What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Statistics
Keisuke Kinoshita focuses on Speech recognition, Speech processing, Reverberation, Speech enhancement and Artificial neural network.
His work on Acoustic model as part of general Speech recognition study is frequently linked to Domain, therefore connecting diverse disciplines of science.
His biological study focuses on Voice activity detection.
The Reverberation study combines topics in areas such as Linear prediction and Microphone.
Keisuke Kinoshita works mostly in the field of Speech enhancement, limiting it down to concerns involving Signal processing and, occasionally, Normalization and Statistical model.
Keisuke Kinoshita has included themes like Ambient noise level and TIMIT in his Artificial neural network study.
His most cited work include:
- Speech Dereverberation Based on Variance-Normalized Delayed Linear Prediction (214 citations)
- A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research (186 citations)
- Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition (182 citations)
What are the main themes of his work throughout his whole career to date?
Keisuke Kinoshita mostly deals with Speech recognition, Speech enhancement, Artificial neural network, Reverberation and Artificial intelligence.
His research integrates issues of Noise and Microphone in his study of Speech recognition.
His Speech enhancement research includes themes of Filter, Spectral density, Microphone array, Noise reduction and Minimum-variance unbiased estimator.
He works mostly in the field of Artificial neural network, limiting it down to topics relating to Beamforming and, in certain cases, Word error rate, as a part of the same area of interest.
As a part of the same scientific study, Keisuke Kinoshita usually deals with the Reverberation, concentrating on Linear prediction and frequently concerns with Linear predictive coding.
His Artificial intelligence study incorporates themes from Blind signal separation and Pattern recognition.
He most often published in these fields:
- Speech recognition (69.19%)
- Speech enhancement (30.81%)
- Artificial neural network (25.25%)
What were the highlights of his more recent work (between 2018-2021)?
- Speech recognition (69.19%)
- Artificial neural network (25.25%)
- Speech enhancement (30.81%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Speech recognition, Artificial neural network, Speech enhancement, Source separation and Algorithm.
Keisuke Kinoshita studies Speaker diarisation, a branch of Speech recognition.
His Artificial neural network study integrates concerns from other disciplines, such as Utterance, Signal processing, Audio signal and Word error rate.
Keisuke Kinoshita combines subjects such as Noise reduction, Spectral density and Reverberation with his study of Speech enhancement.
His Algorithm research incorporates elements of Recurrent neural network and Minimum-variance unbiased estimator.
His biological study spans a wide range of topics, including Blind signal separation, Computer vision and Pattern recognition.
Between 2018 and 2021, his most popular works were:
- All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis (31 citations)
- A Unified Convolutional Beamformer for Simultaneous Denoising and Dereverberation (27 citations)
- Compact Network for Speakerbeam Target Speaker Extraction (26 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Speech recognition
- Statistics
Keisuke Kinoshita spends much of his time researching Speech recognition, Speech enhancement, Artificial neural network, Source separation and Noise reduction.
His Speech recognition research incorporates themes from Time domain, Joint and End-to-end principle.
Keisuke Kinoshita has researched Speech enhancement in several fields, including Algorithm, Filter bank and Filter.
His studies deal with areas such as Estimator, Deep learning and Utterance as well as Artificial neural network.
His study ties his expertise on Reverberation together with the subject of Source separation.
His Reverberation research integrates issues from Mixture model and Convolutional neural network.
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.
