His scientific interests lie mostly in Speech recognition, Speech enhancement, Speech processing, Reverberation and Signal processing. His Speech recognition research is multidisciplinary, relying on both Artificial neural network and Microphone array. His Speech enhancement research includes elements of Noise reduction and Speaker diarisation.
Within one scientific family, Takuya Yoshioka focuses on topics pertaining to Speaker recognition under Speech processing, and may sometimes address concerns connected to Acoustic model and Voice activity detection. His research integrates issues of Deconvolution and Blind signal separation in his study of Reverberation. His Word error rate study combines topics in areas such as Feature extraction and Beamforming.
Takuya Yoshioka mainly focuses on Speech recognition, Speech enhancement, Artificial intelligence, Speech processing and Reverberation. His Speech recognition research integrates issues from Artificial neural network and Noise. His Speech enhancement study combines topics from a wide range of disciplines, such as Background noise, Speaker recognition, Audio signal processing, Noise reduction and Linear predictive coding.
The study incorporates disciplines such as Algorithm and Pattern recognition in addition to Artificial intelligence. His work on Voice activity detection is typically connected to Process as part of general Speech processing study, connecting several disciplines of science. His Reverberation study integrates concerns from other disciplines, such as Blind signal separation and Signal processing.
His primary areas of investigation include Speech recognition, Monaural, End-to-end principle, Word error rate and Speaker diarisation. His study looks at the relationship between Speech recognition and fields such as Joint, as well as how they intersect with chemical problems. Takuya Yoshioka has included themes like Speaker recognition and Data set in his Monaural study.
He usually deals with End-to-end principle and limits it to topics linked to Microphone and Stream processing, Direction of arrival, Contrast, Adaptive beamformer and Robustness. His studies in Word error rate integrate themes in fields like Recurrent neural network and Transformer. Speaker diarisation is closely attributed to Speech enhancement in his research.
His primary scientific interests are in Speech recognition, End-to-end principle, Transcription, Monaural and Speaker diarisation. His Speech recognition research is multidisciplinary, incorporating elements of Speech enhancement and Relevance. His work deals with themes such as Robustness and Microphone, which intersect with End-to-end principle.
He interconnects Speaker recognition, Speaker identification and Joint in the investigation of issues within Monaural. His Joint research incorporates themes from Mutual information, Cluster analysis and Joint probability distribution. His biological study spans a wide range of topics, including Natural and Conversational speech.
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.
Speech Dereverberation Based on Variance-Normalized Delayed Linear Prediction
Tomohiro Nakatani;Takuya Yoshioka;Keisuke Kinoshita;Masato Miyoshi.
IEEE Transactions on Audio, Speech, and Language Processing (2010)
A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research
Keisuke Kinoshita;Marc Delcroix;Sharon Gannot;Emanuël A. P. Habets.
EURASIP Journal on Advances in Signal Processing (2016)
Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition
Takuya Yoshioka;A. Sehr;M. Delcroix;K. Kinoshita.
IEEE Signal Processing Magazine (2012)
The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices
Takuya Yoshioka;Nobutaka Ito;Marc Delcroix;Atsunori Ogawa.
ieee automatic speech recognition and understanding workshop (2015)
Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation
Yi Luo;Zhuo Chen;Takuya Yoshioka.
international conference on acoustics speech and signal processing (2020)
Generalization of Multi-Channel Linear Prediction Methods for Blind MIMO Impulse Response Shortening
T. Yoshioka;T. Nakatani.
IEEE Transactions on Audio, Speech, and Language Processing (2012)
Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise
Takuya Higuchi;Nobutaka Ito;Takuya Yoshioka;Tomohiro Nakatani.
international conference on acoustics, speech, and signal processing (2016)
Blind Separation and Dereverberation of Speech Mixtures by Joint Optimization
Takuya Yoshioka;Tomohiro Nakatani;Masato Miyoshi;Hiroshi G Okuno.
IEEE Transactions on Audio, Speech, and Language Processing (2011)
Blind speech dereverberation with multi-channel linear prediction based on short time fourier transform representation
T. Nakatani;T. Yoshioka;K. Kinoshita;M. Miyoshi.
international conference on acoustics, speech, and signal processing (2008)
CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings
Shinji Watanabe;Michael Mandel;Jon Barker;Emmanuel Vincent.
6th International Workshop on Speech Processing in Everyday Environments (CHiME 2020) (2020)
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: