Speech recognition, Artificial intelligence, Speech enhancement, Speech processing and Word error rate are his primary areas of study. His Speech recognition research incorporates themes from Artificial neural network and Recurrent neural network. Shinji Watanabe has included themes like Natural language processing and Pattern recognition in his Artificial intelligence study.
His Speech enhancement research is multidisciplinary, incorporating elements of Microphone array, Noise measurement and Speaker diarisation. When carried out as part of a general Speech processing research project, his work on Acoustic model is frequently linked to work in Open source, therefore connecting diverse disciplines of study. His Word error rate research is multidisciplinary, incorporating perspectives in Time delay neural network and Machine learning.
His main research concerns Speech recognition, Artificial intelligence, End-to-end principle, Pattern recognition and Artificial neural network. Shinji Watanabe has researched Speech recognition in several fields, including Speech enhancement, Decoding methods and Recurrent neural network. His Speech enhancement research includes themes of Microphone array and Source separation.
His research in Artificial intelligence intersects with topics in Machine learning and Natural language processing. The End-to-end principle study which covers Cluster analysis that intersects with Gibbs sampling. Noise is closely connected to Acoustic model in his research, which is encompassed under the umbrella topic of Pattern recognition.
Shinji Watanabe focuses on Speech recognition, End-to-end principle, Speaker diarisation, Transformer and Artificial intelligence. His work on Word error rate as part of general Speech recognition study is frequently connected to Autoregressive model, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them. His End-to-end principle study integrates concerns from other disciplines, such as Decoding methods, Connectionism and Near and far field.
The study incorporates disciplines such as Voice activity detection, Subtitle, Sequence and Cluster analysis in addition to Speaker diarisation. His Transformer research integrates issues from Self attention, Recurrent neural network, Computation and Reduction. The various areas that he examines in his Artificial intelligence study include Pattern recognition and Natural language processing.
Speech recognition, End-to-end principle, Speaker diarisation, Transformer and Artificial intelligence are his primary areas of study. His Speech recognition study focuses on Source separation in particular. His study explores the link between End-to-end principle and topics such as Near and far field that cross with problems in Signal reconstruction and Transcription.
His research integrates issues of Artificial neural network, Subtitle, Track and Cluster analysis in his study of Speaker diarisation. In his study, Monotonic function and Computer engineering is strongly linked to Recurrent neural network, which falls under the umbrella field of Transformer. His Artificial intelligence study combines topics from a wide range of disciplines, such as Context, Pattern recognition and Natural language processing.
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.
Deep clustering: Discriminative embeddings for segmentation and separation
John R. Hershey;Zhuo Chen;Jonathan Le Roux;Shinji Watanabe.
international conference on acoustics, speech, and signal processing (2016)
ESPNet: End-to-end speech processing toolkit
Shinji Watanabe;Takaaki Hori;Shigeki Karita;Tomoki Hayashi.
conference of the international speech communication association (2018)
Joint CTC-attention based end-to-end speech recognition using multi-task learning
Suyoun Kim;Takaaki Hori;Shinji Watanabe.
international conference on acoustics, speech, and signal processing (2017)
The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines
Jon Barker;Ricard Marxer;Emmanuel Vincent;Shinji Watanabe.
ieee automatic speech recognition and understanding workshop (2015)
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
Hakan Erdogan;John R. Hershey;Shinji Watanabe;Jonathan Le Roux.
international conference on acoustics, speech, and signal processing (2015)
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
Felix Weninger;Hakan Erdogan;Shinji Watanabe;Emmanuel Vincent.
international conference on latent variable analysis and signal separation (2015)
Hybrid CTC/Attention Architecture for End-to-End Speech Recognition
Shinji Watanabe;Takaaki Hori;Suyoun Kim;John R. Hershey.
IEEE Journal of Selected Topics in Signal Processing (2017)
A Comparative Study on Transformer vs RNN in Speech Applications
Shigeki Karita;Xiaofei Wang;Shinji Watanabe;Takenori Yoshimura.
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (2019)
The second ‘chime’ speech separation and recognition challenge: Datasets, tasks and baselines
Emmanuel Vincent;Jon Barker;Shinji Watanabe;Jonathan Le Roux.
international conference on acoustics, speech, and signal processing (2013)
An analysis of environment, microphone and data simulation mismatches in robust speech recognition
Emmanuel Vincent;Shinji Watanabe;Aditya Arie Nugraha;Jon Barker.
Computer Speech & Language (2017)
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: